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

Annotations already disclose readOnlyHint=false, destructiveHint=false and openWorldHint=true, so the agent knows this is a non-destructive mutation with external effects. The description adds nothing beyond that: it does not say what state change occurs, whether the check-in is idempotent or fails if repeated, whether the business is notified, or what the reply_token triggers. For a mutation tool, that is a substantial gap.

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?

It is short and the timing constraint is front-loaded, so nothing is padded. But it is a sentence fragment with no subject or verb, and the brevity comes at the cost of stating the actual action, which is not the same as being concise.

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 two-parameter mutation with no output schema, the missing pieces are the effect of the call and the meaning of booking_id. The timing window does cover the main operational question of when it may be called, but the outcome of the check-in remains unstated.

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 only 50%: reply_token is documented in the schema, but booking_id has no description anywhere. The description never mentions either parameter, so it does not compensate for the undocumented required id (format, source, whether it comes from booking_status or add_booking) and adds no meaning over 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?

The phrase 'When the customer arrives' plus the name/title conveys that this records a customer's arrival against a booking, but the description never states the action outright ('marks the booking as checked in') or what the effect is. It describes a trigger condition rather than the operation, so an agent must infer the verb from the tool name.

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 30-minute-before-booking window is a genuine usage constraint that tells the agent when the call is valid. However, it gives no exclusions or alternatives — nothing about what to do for a booking already checked in, or whether a different tool handles arrival at the front desk.

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