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

Annotations already declare non-readonly, idempotent, non-destructive, and closed-world, so the safety profile is covered. The description adds non-obvious behavior: the receipt token doubles as the requirement token used by request_status and offers, and critically that this action orders nothing — an offer arrives later and is accepted separately, which prevents an agent from assuming a purchase was made.

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 action and its trigger, then the first-versus-revision rule, then the crucial 'orders nothing' caveat. Dense and jargon-heavy ('Joinery', 'receipt token') but every clause carries behavioral information; only the parenthetical about request_status and offers is slightly compressed.

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 six-parameter mutation with no output schema and only half its parameters described in the schema, the description supplies the key semantics an agent needs (token identity, revision meaning, non-ordering nature). It stops short of explaining 'op_id' or the optional contact/action fields, but nothing essential to a correct invocation is missing.

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 50%, so the description must compensate and does so for the two most confusing parameters: 'token' is explained as the requirement's private token that also serves as the request's receipt token, and 'revision' is framed as the revision the buyer saw rather than a server-side counter. 'op_id', 'contact', and the action default remain undocumented in prose, though the schema partially covers 'action' and 'id'.

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 (send the requirement to Joinery) and immediately distinguishes two distinct behaviors: a first send that records the request versus a later send of a changed requirement that records a revision. An agent can tell this apart from edit_requirement or submit_request without opening another 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?

Gives a clear triggering condition ('once the buyer says to') and the branching rule for first versus subsequent sends, including the requirement to name the revision the buyer saw. It does not explicitly say when to use edit_requirement or submit_request instead, so a sibling-selection gap remains.

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