disputes_delete

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

Annotations say destructive/non-readonly, and the description adds substantially more: the preview-vs-execute split, the approval gate and pre-approval settings override, and the side effect that letter files on disk survive deletion. The assistant's inability to self-approve is a critical, non-obvious behavioral fact that annotations cannot express.

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?

Five short sentences, front-loaded with the action, then the confirm semantics, then the side effects and the approval constraint. No filler and nothing repeated from annotations or schema.

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?

An output schema exists, so return-value explanation is unnecessary. For a destructive, approval-gated operation with two parameters, the description covers the safety model, side effects, and the actor constraint — nothing an agent needs 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 0%, so the description carries the burden for `confirm`, and it does: default-false means preview, true means request approval. `id` is left implicit, but "a dispute record" makes its meaning evident. Not a full 5 because the description never explicitly ties the two schema fields to the described behavior by name.

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?

Opens with a specific verb+resource: "Delete a dispute record." That alone distinguishes it from every sibling (disputes_list, disputes_get, disputes_create, disputes_update) without needing to name them.

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?

Clearly explains the two-mode workflow: without confirm=true it is only a preview, with confirm=true the person is asked to approve. It also states a hard constraint — the assistant cannot approve on the person's behalf — which is exactly the kind of guidance that prevents misuse. It stops short of saying when deletion is preferable to alternatives, but no sibling is a plausible substitute for deletion.

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