Skip to main content
Glama
Sentry MCP

Sentry MCP

Official
by getsentry

Submit Feedback to Sentry Team

submit_feedback_to_sentry_team

Report missing, broken, or confusing Sentry MCP tools and ideas to its maintainers, not your Sentry organization, so MCP friction is documented.

Instructions

Report friction with the Sentry MCP server to its maintainers (not the user's Sentry organization): a missing tool, a tool that failed or returned wrong data, a confusing tool, or an idea. Call it at most once per task, only when a Sentry MCP tool was missing, failed, or got in the way. Skip it if the task went fine or did not need Sentry; never use it to log progress or to test it. Do not include secrets or personal data.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "task": "<task>",
      "kind": "<kind>",
      "impact": "<impact>",
      "description": "<description>"
    },
    "name": "submit_feedback_to_sentry_team"
  }
}

Input Schema

NameRequiredDescriptionDefault
kindYesmissing: no tool could do it; broken: a tool failed or returned something wrong; confusing: a tool or its docs were unclear; idea: a suggestion.
taskYesA short phrase naming what the user asked you to do.
impactYesblocked: you could not finish; worked_around: you finished another way; friction: you finished, but it was harder than it should be.
toolNameNoThe Sentry MCP tool the feedback is about, if any.
descriptionYesWhat you tried, including tool calls and any error, and what went wrong.

Output Schema

NameRequiredDescriptionDefault
feedbackIdYesID of the feedback sent to the Sentry MCP maintainers.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Addedv1.0.1

TDQS

A4.6/5.0
Behavior5/5

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

Annotations only declare openWorldHint=true and destructiveHint=false; the description supplies the substantive behavior — the report is routed to maintainers rather than the user's org, there is a per-task rate limit of one call, and secrets or personal data must be excluded. These are real operating constraints an agent could not derive from the annotations.

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?

Front-loaded with the recipient scoping in the first clause, then the gating conditions, then the prohibition on secrets. The opening sentence is long and carries a nested parenthetical, but every clause earns its place and nothing is redundant.

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?

Output schema exists so return values need no explanation, all five params are fully documented in the schema, and the description covers the remaining gaps: recipient, trigger conditions, call frequency, and data-handling restrictions. Nothing an agent needs to decide whether and how to call it is missing.

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%, and the schema already documents the kind and impact enums with per-value meanings plus length limits. The description's prose taxonomy largely restates the kind enum and adds no format or syntax guidance beyond the structured fields, so baseline 3 applies.

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 specific verb and resource (report friction with the Sentry MCP server) and immediately disambiguates the recipient as the maintainers, not the user's Sentry organization — a distinction no sibling tool shares. The enumerated categories (missing tool, failure, wrong data, confusing, idea) pin down exactly what counts as feedback.

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?

Explicit when: only when a Sentry MCP tool was missing, failed, or got in the way. Explicit when-not: skip if the task went fine or didn't need Sentry, never for progress logging, never for testing. It also caps invocation at once per task, leaving nothing to inference.

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