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

Annotations provide readOnlyHint=false, destructiveHint=false, and idempotentHint=false, but no further detail. The description adds valuable behavioral context: it holds the slot for 10 minutes, sends an SMS confirmation, and returns a summary that must be shown verbatim. It also clarifies the terms_accepted requirement. No contradiction with annotations. It stops short of describing what happens if the slot expires, but overall it transparently discloses the core side effects.

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 description is a single well-structured paragraph that front-loads the core action and immediately clarifies the critical distinction (does not create the booking). It packs in the 10-minute hold, SMS, summary requirement, and terms acceptance without rambling. Slightly longer than necessary but every sentence earns its place.

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 tool with 7 parameters and nested objects, and no output schema, the description provides the essential return values (confirmation_id and summary) and clarifies the follow-up create_booking call. It explains the main behavioral flow and constraints. However, it omits any guidance on session_id and invoice_data, which are not self-explanatory from the schema alone. Still, an agent can likely proceed correctly for the common case.

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 description coverage is only 29%, so the description must compensate for under-documented parameters. It mentions quote and slot (implying quote_id and slot_id), customer details (customer object), and terms_accepted, but it does not explain session_id or invoice_data at all. The description adds context beyond the sparse schema but does not fully compensate for the low coverage, especially for optional parameters that could affect the call.

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 states a specific verb (Prepares) and resource (a booking for a chosen slot) and enumerates concrete actions: validates quote and slot, holds the slot for 10 minutes, records customer details and terms acceptance, sends SMS. It also explicitly distinguishes itself from create_booking by stating 'Does NOT create the booking', so an agent can tell them apart without inspecting schemas.

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 gives explicit when-to-use and when-not-to-use guidance: it states that after this call, the customer must read the SMS code and the agent must call create_booking. It also requires explicit customer agreement and terms_accepted=true, leaving no ambiguity about the follow-up flow. This is more than enough to route the agent correctly.

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