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

Annotations say readOnly=false, destructive=false, idempotent=false, so the key question is what actually happens; the description answers it beyond the annotations: nothing is sent or ordered, conflicting or unclear facts return as a single question, and unread words are preserved as written. It also discloses the built-in extensibility of the structured result (each value cites its source words) and the continuation token, which is real behavioral context rather than restatement.

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 dense sentences, front-loaded with the action, then the outcome, then the routing conditions. Nothing is repeated and no sentence is filler, including the closing exclusion rule.

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 tool with a nested requirement object and no output schema, the description fully compensates by explaining the shape of the answer (values tied to source words, one clarifying question, unread text preserved). An agent knows what it will get back and when to reuse the returned requirement handle.

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 100%, so the baseline is 3, but the description adds workflow meaning the schema does not: the requirement object is described as coming from a first answer and being passed in to continue an existing one. That clarification of stateful reuse is the highest-value thing an agent could get wrong here; the utterance and timezone parameters are left entirely to the schema.

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 and resource — reading the buyer's own words into a structured requirement — and describes the transformation result. It explicitly distinguishes itself from both send_requirement (which transmits) and submit_request (which takes already-structured fields), so an agent can route without opening another schema.

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?

It gives an explicit when-to-use (buyer's words, or a correction/addition to an existing requirement) and two named alternatives with their selecting conditions: send_requirement when the buyer says to send, submit_request when fields are already structured. It also states the continuation rule — pass the prior (id, token) — removing any inference about state.

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