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

The description adds value beyond the annotations by disclosing the conditional outcome: 'If the order is fully covered the booking completes immediately (status paid); otherwise the response carries the payment_url for the balance.' This explains the mutation behavior and edge case. It does not contradict the readOnlyHint=false, idempotentHint=false, or destructiveHint=false annotations, and supplements them with actionable context.

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 concise and front-loaded: it opens with the core action and prerequisite, then explains the behavior and outcome. Each sentence contributes new information—code format, coverage logic, and payment_url fallback—with no redundancy. It is slightly longer than minimal, but the extra sentences all serve clarity.

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 output schema exists, the description doesn't need to detail return values, but it still explains the conditional payment_url outcome, which helps the agent anticipate responses. It also covers the code format and the prerequisite, making it sufficiently complete for correct invocation. Minor gaps like error handling are likely covered by the output schema, so this is well-rounded.

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?

The description compensates for the missing schema description of booking_uuid by referring to a 'held booking', implying the UUID's purpose. For the code, it adds format details (XXX-XXXXXX-XXX) and clarifies its origin and role, which are not in the schema. The locale parameter is well-described in the schema, so no additional context is needed. Overall, it bridges the 67% schema coverage gap effectively.

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 action ('Applies a Toots Pass code') on a specific resource ('held booking'), and differentiates this from sibling tools like redeem_gift_card by explicitly identifying the credential type and its role. It also mentions the prerequisite 'after set_contact', which adds clarity about the workflow 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?

The description gives clear context for use: it must be used after set_contact, and it clarifies that the code is a venue credential, not a payment instrument, which helps the agent decide when to select this tool over alternatives. However, it does not explicitly list alternative tools or exclusion conditions beyond the prerequisite, so it stops short of full when/when-not guidance.

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