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

Annotations already signal mutation (readOnlyHint=false) and non-idempotency, but the description adds critical behavioral details beyond those: it places a 15-minute hold, charges nothing, requires no payment info, and mandates a follow-up payment step. It also discloses the authentication requirement (no login) and the idempotency safeguard. No contradiction with 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?

Three sentences, each carrying essential information: the core action and scope, the non-charging hold behavior and required follow-up, and the key constraints. Front-loaded with the purpose, then critical caveats. No fluff or redundancy.

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 tool with 11 parameters and no output schema, the description covers the critical flow, constraints, and next steps. It does not explain what the ID parameters refer to, but sibling tools (search_shoot_types, get_photographer_packages, search_photographers) clearly supply them, so an agent can infer the workflow. The return value is not described, but that is a minor gap given no output schema exists.

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 45%, covering start_time, idempotency_key, address_detail, shoot_detail, and guest_display_name. The description reinforces start_time's 6-hour constraint and idempotency_key's purpose, which are already in the schema, so it adds little new meaning. The many un-described IDs (city_id, package_id, shoot_type_id, photographer_uid) are not explained in the description, though their purpose is inferable from sibling tool names. The description does not compensate for the missing 55% of schema parameter descriptions.

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 action: 'Book a specific photographer for a specific package, date/time, and address on the user's behalf.' It uses a specific verb and resource, and distinguishes itself from sibling tools by being the only creation tool. The mention of the immediate next step (get_payment_link) further clarifies its role in the workflow.

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 provides explicit usage context: it's the tool to create a reservation, it requires no login, and it explicitly instructs to follow with get_payment_link. It also sets constraints (start_time at least 6 hours out, use idempotency_key for retries) which are actionable conditions. It does not list when-not-to-use alternatives, but the flow is so specific that an agent knows when to invoke it.

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