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

Annotations only say this is a non-read-only, open-world, non-idempotent, non-destructive call; the description adds the substance: the recipient is fixed to the email on the booking, the receipt contains booking details and current payment status (paid, reserved with due date, plan, cancelled with refund), and 'You do not see the receipt' sets the return expectation. That is meaningful behavioral context an agent cannot get from 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?

Front-loaded with the trigger and recipient constraint, then content, then accepted identifiers, then the no-email fallback. It is dense with colon-chained clauses and slightly long, but essentially every clause carries decision-relevant 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?

For a four-parameter side-effecting tool with no output schema, it covers the trigger, the fixed recipient, the receipt contents, the fact that the agent gets no receipt back, the accepted identifier forms, and the failure path. An agent could call this correctly without further information.

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 the baseline is 3; the description still adds value by constraining semantics — email/mobile must be the ones the booking was made with, reference is the VU-... code, and taskId applies only to bookings made in this conversation. It does not, however, explain the required-combination logic or precedence among the four optional inputs.

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 and resource ('Vuelo emails it' the receipt/invoice/proof of booking) and frames it around the traveller's request. It is clearly distinguishable from siblings like send_to_payer, resend_link, and contact_support, which are either named as alternatives or implied by the distinct trigger.

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?

Gives an explicit trigger ('When the traveller asks for a receipt, an invoice or proof of a booking'), an explicit prohibition ('never to an address you give'), and a named fallback ('If the booking has no email ... use contact_support'). Nothing about when to call it versus alternatives is left to inference.

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