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

Annotations already mark this as a non-read-only, non-destructive mutation. The description adds substantive behavior: human review for every dispute, no refunds, usual remedy is a redo, and one open dispute per job. That is useful beyond annotations, though it omits post-submission effects or status.

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?

Four short sentences, front-loaded with the action and policy, and the API endpoint equivalence is a compact useful anchor. No filler.

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?

Given full schema descriptions, annotations, and no output schema, the description covers purpose, human review, refund policy, remedy, and uniqueness constraint. It could be more complete by clarifying the request_revision relationship, but otherwise sufficient.

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 job_id, reason, and api_key are documented in the schema. The description adds little semantic context beyond the schema, such as 'job went wrong' for reason and 'one open dispute per job' for job_id, 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?

The description says 'Tell Roster a job went wrong' and 'One open dispute per job,' which clearly identifies opening a dispute on a job. It does not contrast with sibling request_revision or rate_job, so an agent must infer when a dispute is preferable.

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?

It gives a context ('job went wrong') and a constraint ('One open dispute per job'), plus policy that refunds are unavailable and a redo is the usual fix. However, it does not name request_revision as the alternative for a redo or explicitly say when not to open a dispute, so routing remains implicit.

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