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

Nearly everything the annotations cannot convey is disclosed: possible return statuses (created/confirmed/declined), the `unavailable` error path where nothing is booked, the fact that results are candidates until the user permits, and that this is an outward-facing action. One tension: annotations set idempotentHint=false while the description claims idempotency 'by idempotency_key', which frames retry safety as conditional on the key rather than contradicting the annotation outright, but an agent could read the two signals as inconsistent.

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 safety precondition is front-loaded and the booking mechanics follow in a logical order. It loses a point for repetition ('never on your own judgement' and 'Get the user's explicit yes first' restate the same rule) and for generic catalog boilerplate appended at the end.

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 an open-world mutation tool with no output schema, the description covers the essentials an agent needs: gating on user consent, the eligibility condition on the card, the source of the time slot, and the possible outcomes. Only the unspecified response envelope handling and the undocumented note/business_id parameters are left thin.

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 43%, so the description needs to compensate. It does add provenance for start_at ('as check_availability gave it') and explains that idempotency_key governs retry deduplication, but business_id, note and the customer object as a whole carry no added meaning in the description, leaving half the parameter surface documented only by 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?

States a specific verb and resource ('Book a slot in the business's own calendar') and spells out the mechanism: take a start_at from check_availability and the platform books it for the named customer. It is clearly separable from place_order (ordering), request_to_owner (requests) and check_availability (reads) named in the siblings.

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?

Explicit preconditions are given: only call after the user explicitly agrees to the exact what/where/when/who, and only for a business whose card shows a `book` action with method `connected` and no `book` in `cannot`. It also names the upstream source of start_at (check_availability) and the sibling analogue (place_order), so the when-to-use decision is fully determined.

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