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

Annotations only declare the generic profile (readOnlyHint=false, destructiveHint=false, openWorldHint=true, idempotentHint=false); the description adds substantially beyond that: visibility limits (issues are private to you and the team), the two-phase dry-run-then-file behavior, daily quota (10 new items per account per day), cost (free), auth requirement (API key), and a side effect the agent cannot otherwise see — a human is emailed on filing and on every status change.

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

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

Front-loaded with purpose and trigger before mechanics, and no sentence is filler. The middle portion is densely packed into semicolon-and-em-dash chains ('Free; needs a key; 10 new items per account a day'), which reads telegraphically and slightly hurts scannability, but nothing is redundant.

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

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

For a non-idempotent write tool with a nested context object and no output schema, the description covers everything an agent needs: auth requirement, rate limit, privacy of the payload, that the first response is similar issues rather than a filed record, the force override, and the human-notification side effect. No return-value explanation is owed here because it explains the one non-obvious response behavior itself.

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

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

Schema coverage is 100%, so the baseline is 3, but the description earns above baseline by tying parameters to the workflow: where request_id comes from (X-Request-Id header or the error body's request_id), that op should match the failing call's op, and that force: true is specifically the escape hatch when similar issues were returned. It adds little about title/details beyond what the schema already states.

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

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

The description names a specific verb and resource (report a problem / issue) and scopes it with concrete categories: a failing or wrong API call, a wrong or missing boundary, a docs error. That enumeration distinguishes it from an agent's likely confusion partners such as request_feature (new capability) or comment_on_feedback (commentary), and it points at upvote_feedback as the alternative action for a duplicate.

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

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

It gives an explicit trigger condition ('Call it after a call fails in a way that looks like our bug (5xx, a wrong polygon, a boundary that should exist)') rather than a vague 'use when appropriate'. It also resolves the duplicate case: the tool first returns similar issues without filing, and the agent should either upvote_feedback the same one or pass force: true — an explicit alternative path rather than inference.

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