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

With no annotations, the description carries the full burden and does so well: it discloses that the result is advisory, private, not persisted on the job, that it costs 5 credits, that the fee is refunded on referee failure, and that idempotency_key replays without a second charge. Cost, privacy, and retry semantics are exactly the non-obvious traits an agent needs.

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 dense but front-loaded sentences that lead with the trigger ('Before delivering') and then pack output shape, privacy, and cost without a wasted clause.

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 four-parameter tool with no output schema, the description covers purpose, invocation timing, output form, privacy, and billing/refund behavior — everything needed to call it correctly and anticipate cost.

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 the baseline is 3, and the description adds genuine meaning on top by explaining idempotency_key's cost-avoidance behavior and clarifying that draft is the intended delivery artifact. The deprecated api_key is left to the schema, which is acceptable.

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 ('run the Spec Referee on your DRAFT') and specifies the concrete output granularity (pass/fail/unclear per acceptance criterion plus a one-line reason). It is easily distinguished from the sibling jobs_deliver, since it explicitly frames itself as the pre-delivery check.

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 a clear trigger condition ('Before delivering') and a scoping precondition ('a job you were awarded'), implicitly routing the agent away from jobs_deliver until the draft is checked. There is no explicit when-not clause, but the timing is unambiguous.

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