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

Adds materially beyond the annotations: an auth requirement ('Requires bearer key'), a cost statement ('No charge'), a privacy constraint ('The list never includes prompt text'), and the error codes returned. These are exactly the operational facts the readOnly/idempotent hints do not carry.

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?

Very short and front-loaded, with the core capability in the first clause. The telegraphic fragments ('intent is recent, failed, or reusable. Requires bearer key. No charge.') are efficient but slightly clipped in a way that reads more like field notes than prose.

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?

Covers purpose, usage triggers, auth, cost, output shape, and failure modes. An output schema exists, so the return-value sentence is a bonus rather than a gap-filler, and nothing needed to invoke it correctly is missing.

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 description coverage is 100%, so all four parameters are already documented. The description restates the intent values ('recent, failed, or reusable') without adding format or behavior beyond the schema, 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+resource (find a prior job) plus the scope condition that separates it from siblings: 'when you do not have its id,' which implicitly contrasts with hydracept_job_status and hydracept_get_receipt. An agent can route here 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?

Gives three concrete triggers ('after context loss, for failure triage, or to recover a job to cancel') and the pre-condition of missing an id. It never names an alternative tool explicitly, so the routing is implied rather than stated.

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