:hedgehog: PostHog is the leading platform for building self-driving products. Our developer tools – AI observability, analytics, session replay, flags, experiments, error tracking, logs, and more – capture all the context agents need to diagnose problems, uncover opportunities, and ship fixes. Steer it all from Slack, web, desktop, or the MCP.
Python ab-testingai-analyticsanalyticscdpdata-warehouseexperimentsfeature-flagsjavascriptproduct-analyticspythonreactsession-replaysurveystypescriptweb-analytics
feat(signals): shorten the inbox-reports-list tool description (#126008)
Andrew Maguire0b1a121b32b8
diff --git a/products/signals/mcp/tools.yaml b/products/signals/mcp/tools.yamlindex 13182d3495d6..9801a9885295 100644--- a/products/signals/mcp/tools.yaml+++ b/products/signals/mcp/tools.yaml@@ -460,50 +460,22 @@ tools:idempotent: trueenrich_url: '{id}'list: true- title: List signal reports- description: >- List signal reports for the current project. A signal report is a cluster of related observations (signals)- that PostHog has aggregated into a single issue or trend. Reports surface in the Inbox. Supports filtering- by status (potential, candidate, in_progress, pending_input, ready, resolved, failed, suppressed), free-text- search across title and summary, source_product (e.g. error_tracking, session_replay), suggested_reviewers,- `unclaimed`, and `assignee`. `assignee=me` returns only the reports this exact agent claimed, so use it to- find your own work. `assignee=mine` returns every report the user answers for: claims by the user, by any of- their MCP agents, and by internal tasks they started. Claimed reports remain actionable and visible; use- `unclaimed=true` to pick work that has no owner and no draft, open, or unknown PR. Some statuses are hidden- by default (currently suppressed); pass `include_all_statuses=true` to list reports in every status. Do this- when deduplicating against the full inbox state, and read each row's `status` (plus `suppression_source`,- `dismissal_reason`, and `dismissal_note` on suppressed rows) before acting. A suppressed row's- `suppression_source` says whether someone dismissed it (`dismissed`) or a judge held it back before anyone- saw it (`safety_judge`, `not_actionable`, `system`). For picking up work, filter to `ready` — earlier- statuses are still moving through the pipeline, and `pending_input` reports are waiting on a human. Each- report's full work log, including signal findings, judgments, and log entries, is readable via- inbox-report-artefacts-list; read it before acting on a report. Results are paginated and ordered by- '-is_suggested_reviewer,status,-updated_at' by default. To answer "what should I look at next", pass- `view=actionable` with `use_priority_preference=true`, `sort=priority`, and `limit=10`: that returns ready,- actionable reports that have no implementation PR yet, at or above the requesting user's personal- PR-generation threshold, falling back to the project threshold. `use_priority_preference` selects which- priorities to include, and does not order them, so pass `sort=priority` to put P0 first; the default- ordering can put a recently updated P4 above an older P0. Without `limit` a page holds up to 100 reports,- each with its summary. To answer "what needs me", pass `view=for_you` with `sort=priority`: that returns the- open, actionable reports that wait for the requesting user's input, that they claimed, or that name them as- a suggested reviewer, and `count` gives how many there are in total. The other views are `needs_input`- (waiting on a human), `needs_decision` (failed reports, plus actionable ready or pending-input reports- without an implementation PR), `monitoring` (an implementation PR is open), `resolved`, `dismissed`- (suppressed by a person, an agent, a merge, or a closed PR), `held_back` (suppressed by a judge, with- nobody's review yet), `not_actionable`, and `all`. Narrow by reviewer with `scope=for_me`, or- `scope=teammate` plus `teammate_uuid`; the default `scope=entire_project` searches every report. `priority`,- `source_product`, and `scout` each take a comma-separated list. To find the self-driving reports for one- source record — e.g. what the inbox already investigated for a specific support ticket — pass that record's- id as `source_id` together with exactly one `source_product` (for a support ticket:- `source_product=conversations` and the ticket's UUID as `source_id`); add `include_all_statuses=true` to- include dismissed ones. Each row includes typed impact metric metadata and any accessible cached snapshot,- but omits live query definitions and comparisons. Queryless legacy or malformed metrics are always redacted.- Listing reports does not execute metric queries. Each row's `ranking.predictions` carries the inbox ranking- model's predicted probability and lift per outcome (`open`, `action`, `fix`), and `readable`. Lift 1.0 is an- average report. `readable: false` means training could not measure that outcome, so rank and filter on it- with caution. A prediction is a forecast, not the report's state, and `status: unscored` is not a low score.- Order with `ordering=-ranking_<outcome>`, filter with `ranking_min_lift` and `ranking_min_probability` (for- example `fix:2`), and read inbox-ranking-outcomes-list for what each outcome means.+ title: List inbox reports+ description: >+ List inbox reports in the current project. A report groups related findings into one issue or trend. Each+ parameter's description says how it filters.++ For "what needs me", pass `view=for_you` with `sort=priority`. For the next fixable work across the project,+ pass `view=actionable` with `use_priority_preference=true`, `sort=priority`, and `limit=10`. For a personal+ ranked shortlist, such as "my top 10", the prioritizing-my-inbox skill combines these rows with the user's+ activity summary. For the work this agent claimed, pass `assignee=me`.++ Without `limit`, a page holds up to 100 reports, each with its summary. Read a report's work log with+ inbox-report-artefacts-list before you act on it.++ Each row's `ranking.predictions` gives the ranking model's probability and lift for `open`, `action`, and+ `fix`. Lift 1.0 is an average report. A prediction is a forecast, not the report's state, and `status:+ unscored` is not a low score. inbox-ranking-outcomes-list explains each outcome.agent_note: >You may inspect reports without claiming them. A claim indicates active work that should not be duplicated.Before claiming a report, read the report and its work log. If you decide to begin working to fix the issuesdiff --git a/services/mcp/schema/generated-tool-definitions.json b/services/mcp/schema/generated-tool-definitions.jsonindex 50098313b5f7..8f004b813647 100644--- a/services/mcp/schema/generated-tool-definitions.json+++ b/services/mcp/schema/generated-tool-definitions.json@@ -7998,11 +7998,11 @@}},"inbox-reports-list": {- "description": "List signal reports for the current project. A signal report is a cluster of related observations (signals) that PostHog has aggregated into a single issue or trend. Reports surface in the Inbox. Supports filtering by status (potential, candidate, in_progress, pending_input, ready, resolved, failed, suppressed), free-text search across title and summary, source_product (e.g. error_tracking, session_replay), suggested_reviewers, `unclaimed`, and `assignee`. `assignee=me` returns only the reports this exact agent claimed, so use it to find your own work. `assignee=mine` returns every report the user answers for: claims by the user, by any of their MCP agents, and by internal tasks they started. Claimed reports remain actionable and visible; use `unclaimed=true` to pick work that has no owner and no draft, open, or unknown PR. Some statuses are hidden by default (currently suppressed); pass `include_all_statuses=true` to list reports in every status. Do this when deduplicating against the full inbox state, and read each row's `status` (plus `suppression_source`, `dismissal_reason`, and `dismissal_note` on suppressed rows) before acting. A suppressed row's `suppression_source` says whether someone dismissed it (`dismissed`) or a judge held it back before anyone saw it (`safety_judge`, `not_actionable`, `system`). For picking up work, filter to `ready` — earlier statuses are still moving through the pipeline, and `pending_input` reports are waiting on a human. Each report's full work log, including signal findings, judgments, and log entries, is readable via inbox-report-artefacts-list; read it before acting on a report. Results are paginated and ordered by '-is_suggested_reviewer,status,-updated_at' by default. To answer \"what should I look at next\", pass `view=actionable` with `use_priority_preference=true`, `sort=priority`, and `limit=10`: that returns ready, actionable reports that have no implementation PR yet, at or above the requesting user's personal PR-generation threshold, falling back to the project threshold. `use_priority_preference` selects which priorities to include, and does not order them, so pass `sort=priority` to put P0 first; the default ordering can put a recently updated P4 above an older P0. Without `limit` a page holds up to 100 reports, each with its summary. To answer \"what needs me\", pass `view=for_you` with `sort=priority`: that returns the open, actionable reports that wait for the requesting user's input, that they claimed, or that name them as a suggested reviewer, and `count` gives how many there are in total. The other views are `needs_input` (waiting on a human), `needs_decision` (failed reports, plus actionable ready or pending-input reports without an implementation PR), `monitoring` (an implementation PR is open), `resolved`, `dismissed` (suppressed by a person, an agent, a merge, or a closed PR), `held_back` (suppressed by a judge, with nobody's review yet), `not_actionable`, and `all`. Narrow by reviewer with `scope=for_me`, or `scope=teammate` plus `teammate_uuid`; the default `scope=entire_project` searches every report. `priority`, `source_product`, and `scout` each take a comma-separated list. To find the self-driving reports for one source record — e.g. what the inbox already investigated for a specific support ticket — pass that record's id as `source_id` together with exactly one `source_product` (for a support ticket: `source_product=conversations` and the ticket's UUID as `source_id`); add `include_all_statuses=true` to include dismissed ones. Each row includes typed impact metric metadata and any accessible cached snapshot, but omits live query definitions and comparisons. Queryless legacy or malformed metrics are always redacted. Listing reports does not execute metric queries. Each row's `ranking.predictions` carries the inbox ranking model's predicted probability and lift per outcome (`open`, `action`, `fix`), and `readable`. Lift 1.0 is an average report. `readable: false` means training could not measure that outcome, so rank and filter on it with caution. A prediction is a forecast, not the report's state, and `status: unscored` is not a low score. Order with `ordering=-ranking_<outcome>`, filter with `ranking_min_lift` and `ranking_min_probability` (for example `fix:2`), and read inbox-ranking-outcomes-list for what each outcome means.",+ "description": "List inbox reports in the current project. A report groups related findings into one issue or trend. Each parameter's description says how it filters.\nFor \"what needs me\", pass `view=for_you` with `sort=priority`. For the next fixable work across the project, pass `view=actionable` with `use_priority_preference=true`, `sort=priority`, and `limit=10`. For a personal ranked shortlist, such as \"my top 10\", the prioritizing-my-inbox skill combines these rows with the user's activity summary. For the work this agent claimed, pass `assignee=me`.\nWithout `limit`, a page holds up to 100 reports, each with its summary. Read a report's work log with inbox-report-artefacts-list before you act on it.\nEach row's `ranking.predictions` gives the ranking model's probability and lift for `open`, `action`, and `fix`. Lift 1.0 is an average report. A prediction is a forecast, not the report's state, and `status: unscored` is not a low score. inbox-ranking-outcomes-list explains each outcome.","category": "Signals","feature": "signals",- "summary": "List signal reports",- "title": "List signal reports",+ "summary": "List inbox reports",+ "title": "List inbox reports","required_scopes": ["task:read"],"api_operations": ["GET /api/projects/{project_id}/signals/reports/"],"annotations": {diff --git a/services/mcp/schema/tool-definitions-all.json b/services/mcp/schema/tool-definitions-all.jsonindex 48e127e05679..332e5973728a 100644--- a/services/mcp/schema/tool-definitions-all.json+++ b/services/mcp/schema/tool-definitions-all.json@@ -8230,11 +8230,11 @@}},"inbox-reports-list": {- "description": "List signal reports for the current project. A signal report is a cluster of related observations (signals) that PostHog has aggregated into a single issue or trend. Reports surface in the Inbox. Supports filtering by status (potential, candidate, in_progress, pending_input, ready, resolved, failed, suppressed), free-text search across title and summary, source_product (e.g. error_tracking, session_replay), suggested_reviewers, `unclaimed`, and `assignee`. `assignee=me` returns only the reports this exact agent claimed, so use it to find your own work. `assignee=mine` returns every report the user answers for: claims by the user, by any of their MCP agents, and by internal tasks they started. Claimed reports remain actionable and visible; use `unclaimed=true` to pick work that has no owner and no draft, open, or unknown PR. Some statuses are hidden by default (currently suppressed); pass `include_all_statuses=true` to list reports in every status. Do this when deduplicating against the full inbox state, and read each row's `status` (plus `suppression_source`, `dismissal_reason`, and `dismissal_note` on suppressed rows) before acting. A suppressed row's `suppression_source` says whether someone dismissed it (`dismissed`) or a judge held it back before anyone saw it (`safety_judge`, `not_actionable`, `system`). For picking up work, filter to `ready` — earlier statuses are still moving through the pipeline, and `pending_input` reports are waiting on a human. Each report's full work log, including signal findings, judgments, and log entries, is readable via inbox-report-artefacts-list; read it before acting on a report. Results are paginated and ordered by '-is_suggested_reviewer,status,-updated_at' by default. To answer \"what should I look at next\", pass `view=actionable` with `use_priority_preference=true`, `sort=priority`, and `limit=10`: that returns ready, actionable reports that have no implementation PR yet, at or above the requesting user's personal PR-generation threshold, falling back to the project threshold. `use_priority_preference` selects which priorities to include, and does not order them, so pass `sort=priority` to put P0 first; the default ordering can put a recently updated P4 above an older P0. Without `limit` a page holds up to 100 reports, each with its summary. To answer \"what needs me\", pass `view=for_you` with `sort=priority`: that returns the open, actionable reports that wait for the requesting user's input, that they claimed, or that name them as a suggested reviewer, and `count` gives how many there are in total. The other views are `needs_input` (waiting on a human), `needs_decision` (failed reports, plus actionable ready or pending-input reports without an implementation PR), `monitoring` (an implementation PR is open), `resolved`, `dismissed` (suppressed by a person, an agent, a merge, or a closed PR), `held_back` (suppressed by a judge, with nobody's review yet), `not_actionable`, and `all`. Narrow by reviewer with `scope=for_me`, or `scope=teammate` plus `teammate_uuid`; the default `scope=entire_project` searches every report. `priority`, `source_product`, and `scout` each take a comma-separated list. To find the self-driving reports for one source record — e.g. what the inbox already investigated for a specific support ticket — pass that record's id as `source_id` together with exactly one `source_product` (for a support ticket: `source_product=conversations` and the ticket's UUID as `source_id`); add `include_all_statuses=true` to include dismissed ones. Each row includes typed impact metric metadata and any accessible cached snapshot, but omits live query definitions and comparisons. Queryless legacy or malformed metrics are always redacted. Listing reports does not execute metric queries. Each row's `ranking.predictions` carries the inbox ranking model's predicted probability and lift per outcome (`open`, `action`, `fix`), and `readable`. Lift 1.0 is an average report. `readable: false` means training could not measure that outcome, so rank and filter on it with caution. A prediction is a forecast, not the report's state, and `status: unscored` is not a low score. Order with `ordering=-ranking_<outcome>`, filter with `ranking_min_lift` and `ranking_min_probability` (for example `fix:2`), and read inbox-ranking-outcomes-list for what each outcome means.",+ "description": "List inbox reports in the current project. A report groups related findings into one issue or trend. Each parameter's description says how it filters.\nFor \"what needs me\", pass `view=for_you` with `sort=priority`. For the next fixable work across the project, pass `view=actionable` with `use_priority_preference=true`, `sort=priority`, and `limit=10`. For a personal ranked shortlist, such as \"my top 10\", the prioritizing-my-inbox skill combines these rows with the user's activity summary. For the work this agent claimed, pass `assignee=me`.\nWithout `limit`, a page holds up to 100 reports, each with its summary. Read a report's work log with inbox-report-artefacts-list before you act on it.\nEach row's `ranking.predictions` gives the ranking model's probability and lift for `open`, `action`, and `fix`. Lift 1.0 is an average report. A prediction is a forecast, not the report's state, and `status: unscored` is not a low score. inbox-ranking-outcomes-list explains each outcome.","category": "Signals","feature": "signals",- "summary": "List signal reports",- "title": "List signal reports",+ "summary": "List inbox reports",+ "title": "List inbox reports","required_scopes": ["task:read"],"api_operations": ["GET /api/projects/{project_id}/signals/reports/"],"annotations": {