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

Annotations indicate readOnlyHint=false (mutating) and openWorldHint=true. The description adds that an email is sent and the agent must confirm the email with the traveler. It also instructs to avoid mentioning internal details. This goes beyond annotations, but lacks disclosure of failure modes, rate limits, or what happens if the traveler doesn't respond.

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 relatively concise with two main sentences plus embedded instructions. It front-loads the purpose and key steps. However, the instructions are mixed with the purpose, and the structure could be improved with bullet points or clearer separation. Still, every sentence adds value, with no irrelevant 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?

Given the tool has 19 parameters and no output schema, the description covers only the immediate action and prerequisites. It fails to explain the response format, error handling, or what happens after the handoff is initiated. Important context like when the email is actually sent (possible async) or what the tool returns is missing, leaving the agent under-informed.

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?

With schema description coverage at only 42%, the description should compensate but only explicitly addresses guestEmail and emailConfirmedByTraveler. It does not explain other critical parameters like action (though action has enum descriptions in schema), adults, checkIn/Out, etc. The meaning of many optional parameters remains unclear, making it hard for an agent to fill them correctly.

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 clearly states the tool is for 'Internal approval step for quote or booking tools' and specifies it involves sending an email for traveler confirmation. The name 'start_traveler_handoff' aligns with this purpose. It distinguishes from siblings like get_traveler_handoff_status (which retrieves status) and create_provisional_booking (which follows this step).

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 instructions are given: read guestEmail back and confirm before calling, set emailConfirmedByTraveler=true, and tell the traveler to check inbox without mentioning handoff details. It also notes that for BOOKING_HOLD action, use before create_provisional_booking. However, it does not specify when not to use this tool (e.g., if email is already sent or traveler already confirmed).

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