Submit a freee approved-application cancellation

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

Annotations already carry the safety profile (readOnly=false, destructive=true, idempotent=false), and the description adds genuine context beyond them: the resulting application 'may still require approval,' follow-up approval is 'authorized only when the policy expressly covers that chain,' and writes must never be blindly retried. These caveats are consistent with the annotations — no contradiction — and materially shape how an agent should treat the result.

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 sentences of roughly 60 words, front-loaded with the core action followed by two distinct behavioral caveats; every sentence earns its place. The prose is dense and occasionally awkward ('when the exact action or an active scoped business policy is user-authorized'), but the structural economy is good.

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 destructive, non-idempotent write with no output schema, the description covers the essential operational context: ordering after prepare, authorization requirements, approval-chain limitations, and retry caution. It does not describe the return value, failure/error behavior, or what happens to the original approved application, which are notable gaps for a tool of this complexity.

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 (id, reason, confirm, fingerprint) are already documented with types, constraints, and meaning, yielding the baseline of 3. The description's authorization phrasing mirrors, rather than extends, the confirm parameter's semantics and adds no per-parameter detail.

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 states a specific action — 'Create one real cancellation application' — with a clear resource and an ordering constraint, 'after its matching preview,' that distinguishes it from the prepare_cancel sibling and, via the word 'cancellation,' from commit_create/commit_withdraw. The authorization clause is grammatically dense and slightly obscures the core purpose, so it stops short of 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?

Usage context is implied by 'after its matching preview' and reinforced by the schema's reference to 'the matching prepare tool,' signaling a prepared-commit sequence. However, no alternative tools are named and no explicit when-not-to-use conditions are given; 'Never retry an unknown write' is a retry rule, not a tool-selection rule.

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