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

Annotations already declare destructiveHint=true, idempotentHint=true, and readOnlyHint=false, so the bar is lower. The description still earns credit for surfacing the escrow refund, a financial side effect the annotations do not convey. It stays silent on edge cases such as whether the counterparty is notified or whether cancellation is blocked after a claim.

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?

One sentence, no filler, with the action stated first and the side effect second. Nothing to trim.

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 two-parameter mutation with full schema coverage, annotations describing its safety profile, and no output schema to explain, the description covers what an agent needs: the action and its financial consequence. No critical gap remains.

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 both parameters are documented in the schema itself and the baseline is 3. The description adds no format or identity detail for job_id beyond what the schema provides.

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?

The description uses a specific verb+resource ('cancel ... job') and adds the consequential outcome ('refund escrow'), which separates it from adjacent job tools like submit_job, claim_job, and get_job. It doesn't explicitly name a sibling, but the action is unambiguous.

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 qualifier 'your open job' implies a precondition (you must own the job and it must still be open) but never states it as a rule or points to an alternative path when the condition fails. Usage is inferable rather than explicit.

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