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

The annotations only cover the safety profile (readOnly=false, destructive=false, openWorld=false), so the description carries the real burden and does so well: it explains what happens to the input (parsed into structured fields, each value traceable to words), what happens on ambiguity (conflicting or unclear facts return as a single question), and what happens to unparsed text (kept verbatim). It does not mention whether an existing requirement is mutated in place, what the answer object looks like, or any limits, which is the only gap.

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 core action and its effect are front-loaded in the opening clause, and the two exclusions (send_requirement, submit_request) are placed at the end where routing rules belong. The single long sentence packing parse/provenance/question/verbatim is dense but every clause carries information an agent needs; only mild cost is readability.

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?

With no output schema, the description must describe return behavior, and it does: a structured requirement with word provenance, a single clarifying question on conflict, and preservation of unread words. For a stateful, nested-object tool that is close to complete; what is missing is how the caller obtains the id/token to continue and whether a partially-read state persists between turns.

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 schema already documents utterance, turn_id, timezone, and the requirement id/token. The description still adds real meaning beyond it by explaining that the nested requirement object is the handle from a prior answer and that supplying it continues the same requirement rather than starting a new one. It says nothing about turn_id retry semantics or timezone date interpretation, but those are covered in-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 names the specific act (giving the buyer's requirement, or a correction/addition, in their own words) and the specific outcome (it is read into a structured requirement with word-level provenance). It explicitly distinguishes itself from send_requirement (which sends) and submit_request (which takes already-structured fields), so an agent can route without opening a 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 states both when to use this tool and when not to: 'Nothing is sent or ordered: send_requirement sends it when the buyer says so' and 'When you already have the fields in structured form, use submit_request instead.' It also gives the continuation condition ('Pass the requirement (id, token) from the first answer to continue it'), which is the key branching decision for repeat calls.

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