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

Annotations already declare write, non-destructive, idempotent, closed-world, so the safety profile is covered. The description adds genuinely non-obvious behavior: the first send's receipt token becomes the requirement's token used by request_status and offers, and subsequent sends create revisions of the same request rather than new requests. It omits what a send returns and what happens if the token is wrong or the requirement is already live.

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 key branch — first send versus later revision — is front-loaded in the first sentence, and the privacy note on the token is placed adjacent to where it matters. The final sentence is slightly convoluted in phrasing but earns its place by preventing the agent from implying a purchase.

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 6-parameter write with a nested object, no output schema, and only half the parameters described in the schema, the description covers the core semantics well but leaves op_id and contact undefined. An agent can call it correctly with typical inputs, but not without inference on those two fields.

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 description coverage is 50%, and the description meaningfully compensates for two of the undocumented parameters: token (receipt token, keep private) and revision (the revision the buyer saw). Two parameters remain undocumented in both places — op_id (bare string, maxLength 80) and the nested contact object — which for a mutation with a nested parameter is a real gap.

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 a specific verb and resource (send the requirement) and explains the two distinct outcomes — a first send records the request, a later send of a changed requirement records a revision of the same request. It does not name any sibling (submit_request, edit_requirement) as the alternative, so the boundary with those tools is left implicit.

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?

"once the buyer says to" gives a clear trigger condition, and "Name the revision the buyer saw" is a usable rule for the revision parameter. It also sets a scope boundary by stating this orders nothing and that acceptance happens separately on the offer's exact terms. However, it never says when to use edit_requirement or submit_request instead of re-sending, which is the main ambiguity given the sibling list.

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