Mushi-Mushi

Import Sentry issues

import_sentry_issues

Idempotent

Pull existing Sentry issues into Mushi's report queue by IDs or search query for pre-webhook triage. Deduped, idempotent; then triage created reports.

Instructions

Pull existing Sentry issues into Mushi's report queue: by issueIds (numeric ids or short ids like WEB-12, at most 10) or by a Sentry search query (default is:unresolved) within the project's configured Sentry project, limit 1-10. Each issue goes through the same path as a Sentry webhook delivery: deduped per issue, linked, classified. An issue already linked to a report answers linked and is never reopened. Returns { items: [{ input, issueId, shortId, outcome, reportId, error? }], created, linked, failed, indexing }. Write; idempotent; spends classification budget per new report. Needs the Sentry org slug, project slug and an auth token (event:read, project:read) in Integrations → Sentry. Use for issues that existed before the webhook was wired; then call triage_issue on a created report.

Input Schema

TableJSON Schema

Name	Required	Description
`limit`	No	How many issues a query imports (1-10, default 5)
`query`	No	Sentry search query within the configured Sentry project (default is:unresolved). Not with issueIds.
`issueIds`	No	Sentry issue ids or short ids (e.g. "4501", "WEB-12"), at most 10
`projectId`	No	Project UUID. Defaults to configured project. (`project_id` is accepted too.)

Output Schema

TableJSON Schema

Name	Required	Description
`items`	Yes	One entry per requested or matched issue
`failed`	Yes	Issues that could not be imported
`linked`	Yes	Report ids that already existed for these issues
`created`	Yes	Report ids created by this import
`indexing`	Yes	Whether stack-frame files were queued for codebase indexing

Schema Changelog

Changes observed during successful MCP inspections.

Addedv0.1.13Oct 2, 2026

TDQS

A4.6/5.0

Behavior5/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Goes well beyond the annotations: dedupe-per-issue behavior, the fact that an already-linked issue 'answers linked and is never reopened', that each new report spends classification budget, and the auth scopes required. Annotations cover the safety profile (write, idempotent, non-destructive, open-world) and the description reinforces plus extends it.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Dense but front-loaded: the operation and its two modes come first, followed by behavior, return shape, cost, and prerequisites. It is long for a 4-parameter tool and re-states some schema/annotation facts, which keeps it short of a 5.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a write tool that spends budget and has an output schema, the description covers the scenario, side effects, idempotency, auth, and follow-up. Nothing an agent needs to call this correctly is missing, even though the return-shape sentence is redundant given the output schema.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so all four parameters are already documented (limit range, query default and mutual exclusion with issueIds, short-id format, projectId default). The description largely repeats these (at most 10, default is:unresolved) rather than adding syntax or format meaning beyond the schema, so it sits at the baseline.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a precise verb+resource ('Pull existing Sentry issues into Mushi's report queue') and immediately enumerates the two input modes (issueIds vs. search query). An agent can distinguish this from siblings like get_recent_reports or triage_issue without opening the schema.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Explicitly names the triggering scenario ('Use for issues that existed before the webhook was wired') and the follow-up step ('then call triage_issue on a created report'). It also lists required prerequisites (org slug, project slug, auth token with event:read/project:read in Integrations → Sentry).

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.