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

Annotations only declare readOnlyHint=false, openWorldHint=false, idempotentHint=false, destructiveHint=false; the description goes well beyond them by disclosing what happens to the input (provenance per value, conflicts returned as one question, unread words preserved verbatim) and that no order/send side effect occurs. It stops short of covering token secrecy and retry/dedup behavior, which live in the schema rather than the description.

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?

A single dense paragraph, front-loaded with the core action, then outcome, then continuation rule, then the two routing exclusions. Every clause carries distinct information; no filler or restatement of the title.

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 mutation-style ingestion tool with a nested continuation object and no output schema, the description supplies the return shape in prose (structured values with source words, a single clarifying question, unread text retained) and the send/no-send boundary. Minor gaps: privacy of the token and retry semantics are only in the schema, and nothing is said about what happens on an expired or invalid 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 baseline is 3, but the description adds real meaning: it explains that 'requirement' is a continuation handle carried from a prior answer and that the utterance is the buyer's own words including corrections/additions. It does not clarify turn_id or timezone, which the schema already documents.

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: take the buyer's words and read them into a structured requirement, including corrections/additions. It also names the two siblings an agent might confuse it with (send_requirement, submit_request) and the condition that separates them, so an agent can pick it without opening the 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?

Explicit when-to-use ('give the buyer's requirement... in their own words'), explicit when-not ('Nothing is sent or ordered'), explicit alternative ('When you already have the fields in structured form, use submit_request instead'), plus the continuation rule ('Pass the requirement (id, token) from the first answer to continue it'). Nothing about routing 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.