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

Annotations already declare non-destructive and idempotent, so the description focuses on what those hints cannot convey: this is a binding commitment on the person, a stale offer_id returns 409 offer_changed with the current offer, and an unfulfillable change is routed to a human (passed_on) with the agreed terms standing. That is meaningful consequence disclosure beyond the structured fields, though the retry/idempotency nuance is left to the schema.

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 core action and the four accepted offer types before any preconditions, which is the right ordering. The second sentence is heavily nested (consent, terms_sha source, offer_id, stale-offer behavior) and takes real effort to unpack, costing a point, but every clause carries 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?

With no output schema and a binding mutation over 7 parameters, the description covers the outcomes an agent most needs: nothing booked without terms_sha, 409 on a replaced offer, passed_on for unfulfillable changes, and the linked confirmed booking/order result. It does not describe what the returned terms look like or the shape of a successful response, a minor 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?

Schema coverage is 86%, so the baseline is 3, but the description adds real sequencing semantics the schema does not: terms_sha must come from get_item_status and must only be sent after explicit consent to offer.human, and offer_id ties the answer to a specific offer version. It also names what happens without terms_sha, which is behavior the parameter docs alone do not state.

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 (accept) and enumerates exactly what kind of offer is being accepted: a proposed time, a quote, changes to an order, or a change to a confirmed booking/order. It also flags the special case (offer.kind change) so the agent knows the promise is being moved, not a new promise created. Clearly distinct from decline_offer and make_offer in the sibling list.

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 strong conditional: send terms_sha only after the person said yes to offer.human, and states that sending nothing returns the terms to show them. It also explains the fallback path when a change can no longer be made online (passed_on). It never explicitly names decline_offer or cancel_item as the alternative action, so guidance is clear but not exhaustive.

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