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

Annotations already declare readOnlyHint=false and destructiveHint=false, so the write nature is partly covered. The description adds genuinely new context: the reservation is created in the company's reservation system, a confirmation code is returned, and a payment link appears when prepayment is required. It does not warn about duplicate-confirm behavior, which matters given idempotentHint=false, so it falls short of a 5.

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?

Two sentences, zero filler, and the sequencing instruction is front-loaded before the side-effect description. Every clause carries a distinct piece of information.

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?

With no output schema in the structured data, the description compensates by naming the return values (confirmation code, conditional payment link). It also covers the token precondition and the reservation side effect, so an agent has everything needed to invoke it 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 100%, so 3 is the baseline. The description goes beyond it by explaining what confirmation_token actually represents — proof that the customer saw that exact summary — which clarifies why it must be echoed verbatim rather than regenerated. Other parameters are left to 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+resource ('Confirm the booking') and then names the actual side effect ('Creates the reservation in the company's reservation system'), plus the return payload. An agent can distinguish it from siblings like select_offer or provide_customer_details without opening any schema.

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 precondition is explicit: pass the confirmation_token returned by the previous call, which proves the customer saw that exact summary. That establishes the correct point in the flow. It stops short of naming an alternative tool or stating when not to use it (e.g. if the customer wants to change the offer first), so it is clear context without exclusions.

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