job_verdict

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

Goes well beyond the annotations: it discloses exactly what gets written (a human-confirm evidence row via the same path as POST /api/evidence, which triggers confirm push files, plus a milestone event) and what failure state to expect (conflict when the job is not running or has no linked test run). This is precisely the mutation-side context the readOnly/destructive hints cannot convey.

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 action front-loaded, then mechanics, then the failure precondition. The parenthetical about confirm push files is jargon but load-bearing for anyone reasoning about side effects. Nothing is redundant with the title or schema.

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?

An output schema exists, so return shape need not be described, and the description covers the mutation's side effects and validity gate. What is left implicit is repeat behavior — the annotation declares non-idempotency, but the description doesn't say whether re-submitting a verdict for the same step is allowed or errors.

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 80%, so the schema already explains step, notes, job_id, source, and the verdict enum — including the non-obvious 'coordinator' source convention. The description adds no per-parameter meaning (e.g. what makes a step id valid, or how a re-answer on the same step behaves), so the 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 resource: answering a running job's current step with a pass/fail/skip verdict. It also distinguishes the mechanics from plain evidence recording by naming the POST /api/evidence path. It stops short of explicitly contrasting with the closest siblings (job_event, job_finish, add_evidence), which an agent must infer.

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?

The description supplies a hard precondition — the job must be running and linked to a test run, otherwise conflict — which effectively tells the agent when this call is valid. However, it never names an alternative for the adjacent cases (e.g. use job_event for a non-verdict event, job_finish to close the job), so the routing guidance is implied rather than explicit.

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