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

Annotations already flag destructive=true, idempotent=true and non-read-only, so the bar is lower, yet the description adds real context: it blocks on missing facts and atomically assigns a number. It does not spell out what an atomic failure looks like or whether numbering is irreversible, leaving a small gap.

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?

Two compact sentences, no filler: the precondition and the atomic numbering behavior come first, then the scope exclusions. Every clause carries operational meaning for the agent.

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 5-param, destructive, idempotent mutation with no output schema, the description supplies the gating condition, validation behavior, atomicity, and explicit non-goals; return value need not be described since no output schema exists and the key outcome (assigned number) is stated.

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 60%, and the description compensates by tying the call to the user-approved "total" (expected_total_minor) and the confirmation gate (confirmed). It does not clarify request_id retry semantics or business_id scoping, but the schema covers those directly.

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?

Specific verb+resource: "Finalize a draft" invoice, with the exact precondition (user approval of contents, tax treatment, total). The closing sentence explicitly disclaims adjacent capabilities (sending the document, certifying tax compliance), which separates it from invoice_draft and any send/tax tools in the sibling list.

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 states the trigger condition — only after the user approves the exact contents and total — and implies the prerequisite draft-creation sibling without naming it. It also states a negative boundary (does not send or certify tax). No alternative tool is named by name, so it falls just short of a 5.

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