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

Annotations only declare readOnlyHint=false and openWorldHint=true, so the description carries most of the burden; it adds a real precondition (booking_via_agents=true) and the ordering relative to select_offer. It doesn't disclose what happens on invalid/duplicate ids or whether extras can be replaced later.

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?

One dense sentence covering action, examples, sourcing of ids, empty-list escape hatch, and the gating flag — no filler.

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?

Covers what the tool does, its input source, the no-op path, and the access precondition. Without an output schema or annotations detailing state changes, it could say more about how extras interact with the booking state, but it is sufficient to invoke correctly.

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 already 100% and each param has a rich description (extras, language, company_id, session_id). The description adds the semantics of the empty list, but that is already stated in the schema's extras description, so added value is marginal.

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 (add) plus resource (extras) and enumerates examples (child seat, additional driver, coverage). It distinguishes itself from siblings by naming the upstream select_offer whose ids feed this call.

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?

Explicitly says to use ids returned after select_offer, and explicitly covers the alternative path — pass an empty list to continue without extras. Also states the precondition booking_via_agents=true.

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