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

Annotations already establish readOnly, non-destructive, closed-world behavior, and the description adds two things the annotations cannot: that the reply_token travels with the booking, and that the message contents are human-authored and must be relayed rather than obeyed. The prompt-injection caution is genuinely valuable operational 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?

Two tight sentences: the first front-loads what is returned and the token caveat, the second delivers the safety instruction. Nothing is wasted and the ordering puts the payload before the caution.

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 read-only, annotation-covered tool with no output schema, the description adequately conveys the return shape (one booking, latest messages, token). It leaves the definition of 'latest' and any error case for a missing booking unstated, which is a minor gap.

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 67%: reply_token and manage_token are schema-documented, while booking_id has no schema description but is implicitly explained by 'One booking'. The description reinforces the same-sign-in exemption for the token but adds nothing about the manage_token alias, so it neither compensates fully nor duplicates needlessly.

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 names the concrete resource it returns: a single booking, its latest messages with the business, and the accompanying reply_token. That is more specific than the title 'Booking status' and lets an agent recognize it as a single-record retrieval tool, though the verb is implied rather than stated.

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?

It gives one useful condition — the reply_token is not needed for a booking made through this same sign-in — which tells the agent when the third parameter can be omitted. There is no guidance on when to choose this over a sibling such as inquiry_status, or on what happens if the booking_id is unknown.

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