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

Annotations already declare non-read-only, idempotent, non-destructive, closed-world, but the description adds real substance: what record is created on first send, that the requirement token doubles as the receipt token used by request_status and offers, that repeat sends produce revisions rather than new requests, and that no order is placed. This is exactly the kind of consequence-level disclosure an agent needs before invoking a write tool.

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 trigger, and every clause carries information. The nested parenthetical explaining the receipt token is dense and slightly hard to parse on first read, but little is wasted.

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 mutation tool with no output schema, the definition covers the lifecycle consequences well (request vs revision, token reuse, no ordering). It falls short only on the operational parameters (op_id, action, contact), which remain undocumented outside a partial schema.

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 50% schema coverage, the description usefully constrains `revision` ('Name the revision the buyer saw') and reinforces the privacy role of `token`, which the schema also covers. It says nothing about `op_id`, `action` (including the quote default), or the nested `contact` object, leaving half the parameters to the schema alone.

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 Stillleaf') plus the target and the two distinct outcomes (first send = records the request; later send of a changed requirement = records a revision of the same request). An agent can tell this apart from the request-status and offer siblings the description names.

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 trigger ('once the buyer says to') and states the negative boundary that matters most ('This orders nothing: an offer comes later and is accepted separately on its exact terms'). It does not resolve the obvious overlap with edit_requirement or submit_request, so the agent must infer which tool to use for corrections.

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