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

Annotations declare a non-read-only, non-destructive, non-idempotent mutation, and the description adds real behavior beyond that: each extracted value is traceable to source words, conflicts or ambiguity return as a single question, and unparsed words are preserved verbatim. It also discloses the continuation handshake via requirement id/token. It doesn't cover idempotency explicitly, though the schema's turn_id handles that — a minor omission, so not a 5.

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?

Dense but front-loaded: what it does first, then the continuation contract, then the safety boundary, then the alternative tool. Every clause carries information an agent needs; no filler.

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?

Covers purpose, continuation flow, non-sending guarantee, and the structured-fields alternative, which is what an agent needs for a nested-object tool with no output schema. What the answer actually looks like (question vs. structured requirement fields) is described only in outline, and no return shape is given since no output schema exists — a small gap.

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 baseline is 3; the description adds meaning by instructing that the requirement object (id, token) comes from the first answer and is how a requirement is continued. It also implicitly frames utterance as the buyer's verbatim words and timezone as date-reading context, though turn_id's retry semantics live only in 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?

States a specific verb and resource: read the buyer's own words into a structured requirement, with the added scope of corrections/additions. It explicitly distinguishes itself from send_requirement (sending) and submit_request (already-structured fields), so an agent can pick it out of a crowded 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?

Explicit when-to-use (free-text requirement, correction, or addition), explicit when-not (don't use when fields are already structured — use submit_request), and explicit about what it isn't (nothing is sent or ordered — send_requirement does that). Names the continuation path via the requirement id/token from the first answer.

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