Merge fix PR

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

Annotations already declare destructiveHint and idempotentHint, yet the description still adds real value: no unmerge endpoint exists, recovery requires a manual revert PR outside this tool, and re-running an already-merged attempt is a safe no-op. It further discloses the hold-refusal authority model (only a human in the console can override with a reason) and warns that review text is model output from untrusted input — none of which is inferable from structured fields.

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 correctly — action, return shape, then risk, then failure modes, then prerequisites and alternatives. It is dense but nearly every clause carries distinct operational information. Minor waste in restating 'Returns { merged, reportStatus }' when an output schema exists, and the middle sentences run long as chained clauses.

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 destructive, open-world write with an output schema, the agent needs irreversibility, idempotency, error semantics, and prerequisites — all four are present, including the escalation path for a refused merge. Return values are covered by the output schema, so the description's brief mention is a bonus rather than a gap.

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% and both parameters are documented, so the schema does the heavy lifting and the baseline applies. The description does add a small amount: 'squash-merge' implies the default merge method, though it never mentions mergeMethod or the merge/rebase alternatives, leaving the enum's non-default options entirely to the schema.

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?

Opens with a concrete compound verb set (squash-merge the PR, mark the report fixed, notify the reporter) naming both the resource and the side effects. It explicitly distinguishes itself from two siblings — dispatch_fix as the upstream opener and transition_status as the state-only alternative — so an agent can separate them without opening any schema.

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?

Usage is stated positively ('use to ship a fix opened by dispatch_fix'), negatively ('use transition_status to change state without merging'), and gated by prerequisites (CI green via refresh_ci, user confirmation on unreviewed PRs). It also names the two blocking responses and what to do for each: 409 REVIEW_HOLD is not overridable here, 409 REVIEW_PENDING means wait and retry.

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