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

Annotations already declare readOnlyHint=false and openWorldHint=false, so the write nature is known; the description adds real value by disclosing the write-key requirement and how to pass it on the sandbox door. It still omits the effect of a dispute (what changes on the job, reversibility, whether funds move).

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 short sentences, front-loaded with the core action before the auth detail. The sandbox sentence is slightly run-on but every part carries information.

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 mutation with no output schema and low schema coverage, the definition covers auth and idempotency but leaves the dispute's side effects and two parameters unexplained. Adequate to attempt a call, but not fully self-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 coverage is only 25%, so the description must compensate; it does explain apiKey sourcing via get_sandbox_key and that idempotencyKey is required. However jobId and mandateId are left entirely undocumented in both schema and description.

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?

"Dispute a delivery" is a specific verb+resource that an agent can distinguish from accept, deliver, and request_revision. It lacks an explicit statement of how it differs from the other negative-response sibling request_revision, keeping it just under a 5.

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 states operational prerequisites (write key, idempotencyKey) and a sandbox-specific instruction, but never says when to dispute versus request_revision or cancel. Usage context is implied rather than spelled out.

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