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

Annotations already declare readOnlyHint=false and destructiveHint=false, so the mutation and safety profile are covered. The description adds genuinely non-obvious behavioral meaning beyond that: recording completion does not itself mean the fix is real — 'counts only once a later read finds it passing' — which steers the agent toward mttr_rescan before reporting success.

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?

Two short sentences, front-loaded with the action and id source before the caveat. The second sentence ('counts only once a later read finds it passing') is slightly oblique and takes a beat to parse, but every sentence carries necessary information.

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 one-parameter, non-destructive state-change tool with full schema coverage and annotations, the description covers the essentials: where the id comes from and how completion is validated. It omits idempotency (calling twice on the same id) and error behavior for unknown or already-completed ids.

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 the single parameter is already documented as 'The task id from mttr_queue.' The description repeats the same provenance ('by its id from mttr_queue') without adding format, range, or error semantics, so baseline 3 applies.

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 state change ('says a queued task is done') against a specific resource ('queued task'), scoped by 'its id from mttr_queue'. That implicitly separates it from mttr_queue (the lister) and mttr_rescan (the verifier), both of which are named or referenced.

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?

Gives clear context for use (after a queue task is fixed) and names the alternative/follow-up tool explicitly: 'ask for a fresh read with mttr_rescan'. It stops short of stating when not to call it or what happens if the id is stale/already done, so it is clear context without full exclusions.

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