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

Annotations only cover readOnly/idempotent/destructive/openWorld; the description goes well beyond them by disclosing that the hold is a real prebook with a locked price, that the payment_url is opened by the human, and that the agent never handles card details. It also warns the return may carry a different final price plus change warnings.

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?

Four dense sentences, front-loaded with the core behavior and the payment_url return, then prerequisites, then edge-case handling. Every sentence carries information relevant to correct invocation; only the double-dash phrasing adds slight friction.

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?

There is no output schema, so the description carries the return-value burden and does so fully (payment_url, final price, change warnings). For a 6-parameter mutation with openWorld semantics, the operational guidance about confirming details and relaying price changes closes the remaining gaps.

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 only 50%, so the description must compensate. It conveys that guest name/email are required and that the offer is the 'chosen offer' (tying back to get_live_rates), but it says nothing about agent_name or guest_phone, leaving those 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 precise scope: holds the offer, registers guest details, returns a payment_url, while explicitly excluding payment handling. This lets an agent distinguish it from get_live_rates (which supplies offer_id) and booking_status (which likely tracks the result) without opening any schema.

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 an explicit precondition — confirm the guest's name and email with the user before calling — and a post-call obligation: relay any price change before sending the user to pay. It lacks an explicit when-not or a named alternative sibling, but the context is clear enough to route correctly.

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