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

Annotations already declare destructive, idempotent, openWorld, non-readOnly, but the description adds real operational nuance the annotations cannot: idempotency is keyed on operation_id plus revision, a new operation risks duplication, and a timeout is not proof of absence so unknown states require reconciliation. That substantially lowers the risk of an agent double-applying an approval.

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?

Three tight sentences with the core action front-loaded and no filler. The phrasing is dense and slightly telegraphic ('Timeout is not absence'), but each sentence carries distinct operational weight.

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?

With an output schema present and annotations covering the safety profile, the description only needs to cover preconditions and failure semantics, and it does both. Missing only explicit routing to the reconcile/unknown-resolution siblings for the ambiguous case it raises.

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 baseline is 3. The description does add conditional meaning the schema lacks — assignee_id matters for create, target_issue_id for link, expected_revision must be exact — but it does not explain formats or what happens if a conditional field is omitted for the wrong action, so the gain is modest.

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 — approving an exact proposal revision to create or link under tracker authority — which lets an agent tell it apart from engineering_reject and engineering_propose. It does not name those siblings explicitly, so differentiation is inferred from verbs rather than stated.

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 concrete preconditions for each branch: create requires an available assignee, link requires a verified candidate target. Retry guidance ('identical decision with original operation_id/revision retains retry identity') tells the agent how to behave on re-invocation, though it never names engineering_reconcile or engineering_resolve_unknown as the escalation path.

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