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

Annotations already declare the write-but-non-destructive, idempotent, closed-world profile. The description adds real behavioral context beyond them: acceptance is computed and only holds when nothing is rejected, the business replies with a proposed remedy via the inspect_offer thread, the call is refused if terms have changed since terms_sha256, and no payment or refund occurs here.

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 purpose is front-loaded, but the prose is telegraphic and grammatically tangled ('with a reason for a rejection, optionally for one portion of the order'; 'Recorded for the business, which answers a rejection in inspect_offer thread.fulfilment'). The content earns its place, yet the phrasing forces the reader to re-parse several clauses.

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 non-destructive idempotent write with a rich schema but no output schema, the description covers the key downstream consequences (remedy proposed by the business, no payment movement) and the terms-drift refusal. What is missing is how errors or partial rejections surface and how the record relates to later remedy acceptance.

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 71%, so the schema does most of the work, but the description meaningfully clarifies the domain: lines map to indices in terms.items, the portion scopes the inspection to one part of the order, and the rejection reason attaches to rejected quantities. It does not discuss name, note, id, or token, but those are documented in the schema.

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 opens with a specific verb and resource: recording the buyer's inspection of a placed order, with accepted/rejected quantities per line item. It implicitly distinguishes itself from the read-only inspect_offer by describing what is recorded rather than what is read, though the contrast is never stated outright.

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?

Usage is only implied: the tool applies after an order has been placed, and a buyer who rejects something should expect a response through the inspect_offer thread. There is no explicit when-to-use or when-not-to-use statement, and no direct naming of alternatives such as release_payment or answer_remedy.

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