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

Annotations already declare idempotentHint=true and destructiveHint=true, and the description deepens both: it reveals the exact 15-minute expiry window, that a 6-digit code is deployed to email or phone, and the precise idempotent behavior (returns the original reservation without resending the code). This is exactly the kind of behavioral context that goes beyond structured hints, and nothing contradicts the annotations.

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 sentences, every one earns its place: purpose, return value and side effect (code sending), workflow routing, expiry, and idempotency. Critical information is front-loaded (what it does) before secondary detail (idempotency). Zero filler or repeated schema content.

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 complex 7-parameter tool with nested objects, the description plus a 100%-covered schema and an output schema cover everything an agent needs: return shape (already in output schema), contact delivery semantics, expiry, idempotency, and follow-up routing. Nothing material is missing.

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 100% and the schema is extraordinarily rich, even embedding flow guidance ('a hold nobody can confirm is worse than a refused call') inside the phone parameter. The description adds marginal param-level value — it ties customer_contact to code delivery and idempotency_key to the re-call behavior — but mostly reinforces what the schema already states. Baseline 3 is correct given the high schema coverage.

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 ('Reserve a time slot at a business') and immediately orients the agent in the broader workflow by naming the follow-up tool (confirm_booking) and the pending_offer state. This clearly separates it from siblings: get_availability (checking slots) and confirm_booking (finalizing) are distinct steps in the same flow, so an agent can tell exactly where this tool sits.

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 description explicitly routes the agent forward to confirm_booking ('The customer reads the code back to confirm via the confirm_booking tool') and explains the lifecycle (pending offer, 15-minute expiry). It does not explicitly state negative conditions such as 'use get_availability before reserving' or when NOT to call it, so the guidance is strong on sequence but slightly short on exclusion criteria.

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