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

Annotations mark it as a non-destructive, non-idempotent write, and the description adds real behavioral context beyond that: each extracted value is traceable to its words, conflicts come back as a single consolidated question, and unread text is preserved verbatim. It also removes the biggest risk of misreading 'send' intent by asserting nothing is sent or ordered. Minor gap: it never plainly says a requirement record is persisted and that later turns depend on that state, though the continuation sentence implies it.

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 core action, then the output shape, then the continuation rule, then the safety note and the alternative tool. Dense but every clause carries information an agent needs; the sentences are long and chained, which costs a bit of readability but not correctness.

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-parameter tool with a nested requirement object and no output schema, the description covers what comes back (structured values with word provenance, a single clarifying question) and how to keep the session going. Left unmentioned: how timezone affects date reading and how turn_id deduplication behaves, though the schema documents both.

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; the description earns above that by explaining the conversational semantics of `requirement` – it is the handle from the previous answer and must be carried forward to continue the same requirement. The utterance/requirement distinction (new words vs. continuing context) is clarified in a way the schema fields alone do not convey.

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 and resource: read the buyer's own words into a structured requirement, including corrections or additions. It explicitly separates itself from send_requirement (which actually sends) and submit_request (for already-structured fields), so an agent can place it among siblings without reading their 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 explicit routing: use this when the buyer speaks in their own words, use submit_request when the fields are already structured, and call send_requirement only when the buyer confirms. It also states the continuation path (pass the requirement id/token from the first answer), which is exactly the decision an agent faces on turn two.

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