Publish an approved LocalMCP GitHub issue

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

Goes well beyond the annotations by disclosing draft TTL (15 minutes), process ownership, the returned issue URL, and the no-auto-retry policy — none of which the hints convey. There is mild tension with idempotentHint=true, since the description warns against retrying uncertain results, which limits the practical value of that hint; a reader could be confused about whether a retry is safe.

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?

Dense and front-loaded: the approval precondition arrives in sentence two, before any operational caveats. Slight redundancy between 'never submit automatically after an error' and 'do not automatically retry uncertain results' keeps it off a perfect score.

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 two-parameter mutation with no output schema, the description supplies the return value, the safety precondition, the draft lifecycle (15-minute expiry, process-scoped), and the failure-handling policy. Nothing an agent needs to call it correctly is missing apart from parameter mapping.

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 description coverage is 0% and the description compensates only indirectly by referencing the feedback_prepare draft. It never explains that draft_id is the UUID returned by feedback_prepare, nor that confirmation must be the literal string 'publish' — the most likely source of a malformed call.

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?

States a specific verb and resource ('Publish a feedback_prepare draft') and names the sibling tool that produces the input, making the prepare/publish pairing unambiguous. Adds the auth context ('under the user's existing gh login') which no structured field carries.

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?

Explicitly states the precondition ('Call only after explicit user approval of that draft's repository, title and body') and two hard exclusions ('Never submit automatically after an error' and 'do not automatically retry uncertain results'). An agent knows exactly when it may and may not invoke this tool.

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