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

Annotations already declare this is a non-read-only, idempotent, non-destructive write, so the description's job is to say what the write actually causes. It explains that the answer is recorded for the business, which applies it on its side, and that an ACCEPT of credit or refund moves no money until the payment processor records it. That is meaningful side-effect disclosure beyond the annotations; only failure/retry behavior is left implicit.

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?

Three sentences, front-loaded with the action and followed by effect and then payment/money clarification, with no filler. The middle sentence is slightly convoluted in phrasing but still carries distinct information.

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 with no output schema and only 57% schema coverage, the description covers the important side-effect semantics but is thin on the optional note and on what the caller receives back after answering. An agent can call it correctly, but some parameter-level semantics are left to the schema or unstated.

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?

Coverage is 57%, so the schema already documents id, name, token, and terms_sha256 while remedy_id, answer, and note have none. The description usefully explains where remedy_id comes from (the PROPOSED remedy in the offer thread) and what ACCEPT/DECLINE mean at a business level, but leaves note and name unaddressed, which matches the baseline 3 rather than exceeding it.

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?

Uses a specific verb pair (accept/decline) on a specific resource (a remedy proposed by the business on a placed order), which is concrete enough to act on. It does not explicitly distinguish itself from the sibling tools accept_offer and decline_offer, so an agent must infer that this one targets a remedy object rather than an offer.

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?

The parenthetical tells the agent exactly where the input comes from (inspect_offer thread.fulfilment.remedies with state PROPOSED), which is genuine when-to-use guidance tied to a prerequisite. It stops short of naming exclusion cases, such as what to do when no remedy is in PROPOSED state.

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