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

Annotations only say non-read-only, idempotent, open-world, non-destructive. The description adds real behavioral context: existing unclaimed cards are claimed instead of duplicating a profile, waiting requests transfer to the card, the platform verifies the applicant via the company's official contacts, and a security restriction (never send ЭЦП files or passwords).

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?

Front-loaded with the trigger and the claim-vs-create distinction, then the fallback and guardrails. Dense but each clause carries information; a few long sentences and filler like 'Nothing else is required' slightly dilute it.

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 6-param mutation tool with no output schema, it covers the verification flow, the not_found error path, idempotency expectations, and safety constraints. It stops short of describing the success response shape or how long verification/handover takes, which would help an agent set expectations.

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?

With 83% schema coverage the baseline is 3, but the description adds meaning beyond the schema: note and email should only be supplied if the human already stated them, and the email must not be one that already owns a profile. It also frames name-based lookup as returning ambiguous matches, complementing the schema note.

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?

States a specific verb+resource: claims an existing registry card for a company rather than creating a second profile. It explicitly contrasts with save_party for the not-found case, so an agent can distinguish it from the closest sibling without opening schemas.

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?

Gives trigger ('Your human says «add my company»: call this first'), the fallback path (not_found → save_party with kind organization), and an explicit exclusion ('Use a key that has not published for anyone else'). Conditions for optional params are also bounded.

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