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

With annotations providing readOnlyHint=false, idempotentHint=true, and destructiveHint=false, the description adds crucial context beyond those clues: it explains exactly what is not done (no quoting, pricing, selling, payment, or binding), that consent is mandatory and how it must be obtained, what happens on success (status 'received', a reference), and the idempotent behavior of repeats within the same conversation — including the nuance that a genuinely failed request returns delivery_failed and isError and is worth retrying.

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?

The description is well-structured and front-loaded with purpose and boundaries, but it is somewhat lengthy. Every sentence carries useful information about consent, refusal of extra fields, and idempotency, so it earns its place, though it could be slightly tightened.

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?

Despite six parameters, a strict schema, and an output schema, the description covers all the essential behavioral and procedural details an agent needs: consent requirement, accepted fields, refusal of extra data, success response, idempotency, and retry conditions. Nothing critical 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 100%, so the baseline is 3, but the description adds substantial meaning beyond the schema: it clarifies that consent must be in the customer's own words, that only the service, name, phone, consent, and language are accepted, and that extra data like an address, ID number, immigration status, or date of birth is refused rather than dropped. This directly explains the additionalProperties: false and the required list.

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 verb (leaves the customer's name and phone number) and resource (a request for an affiliate to call about a service), and it immediately draws boundaries that distinguish it from siblings: it does not quote, price, sell, take payment, or bind coverage. Sibling tools like apply_as_provider or list_services are clearly separate.

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?

The description gives explicit when-to-use prerequisites (ask for consent in the customer's own words), when-not-to-use guidance (do not call again for the same customer and service), and describes retry conditions (only when the request genuinely failed). Nothing is left to inference.

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