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

Beyond the annotations, it discloses the parsing behavior (each value records its source words), the conflict handling (unclear facts return as a single question), and that unread text is retained verbatim — none of which the annotations convey. It stops short of stating what a first call returns or any token/permission lifecycle beyond keeping the token private, which the schema already covers.

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 alternative routing, all in three efficient sentences. A semicolon-heavy structure but no filler sentences.

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 4-parameter tool with a nested object and no output schema, the description covers inputs, continuation, return behavior (provenance, clarifying question), and state retention. Only the first-call behavior (creating a new requirement) is left implicit rather than stated.

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 real meaning: the utterance should be in the buyer's own words verbatim, and the requirement object is the continuation handle from a prior answer. It doesn't add anything about timezone or turn_id, which the schema handles well.

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 words into a structured requirement — and distinguishes it from send_requirement (which actually sends) and submit_request (which takes already-structured fields). An agent can route between all three 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 explicitly covers the when (free-text need, correction, or addition), the when-not (fields already structured → use submit_request), the sequencing rule (nothing is sent until send_requirement), and how to continue an existing requirement via the id/token pair.

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