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

Annotations already declare the write-but-non-destructive, idempotent profile, so the bar is lower. The description still adds real context: the send orders nothing, an offer follows later and is accepted separately on its exact terms, and the requirement's own token doubles as the receipt token for request_status and offers. It does not mention what the idempotency behavior means in practice for op_id, which is the one notable 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?

Compact and front-loaded: the action, the record-vs-revision rule, then the boundary (this is not an order). The clause structure is dense and slightly idiosyncratic, but every sentence carries a distinct, useful fact with no filler.

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 7-parameter mutation tool with no output schema, the description covers what is created (a request or a revision), the receipt token returned, and what the call does not authorize. The remaining omissions are op_id handling and the role of the contact/action fields, which is a modest but real gap.

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?

With 57% schema coverage, the description does compensate for some undocumented parameters: "revision" has no schema description but is clarified as the revision the buyer saw, and "token" gains its downstream role. However, "op_id" (an obvious idempotency key needed to exploit idempotentHint) and "contact" are entirely unexplained in both schema and description, so compensation is partial.

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: sends the requirement to Decant, and explains that the first send creates the request while a later send of a changed requirement records a revision. That is well beyond a restatement of the name. It does not say how this differs from nearby siblings such as submit_request, edit_requirement, or submit_purchase_order, so an agent must infer the boundary.

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, and the first-send/revised-send split implies when to use it again. However, it never states when NOT to use it (e.g., when to call edit_requirement to change a draft requirement instead of re-sending), and no alternative sibling is named. Usage is implied rather than spelled out.

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