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

Annotations already declare readOnly, idempotent, and non-destructive, so the safety profile is covered. The description adds real value by enumerating the state machine the tool reports on and noting that 'payment pending' includes the payment link, letting the agent interpret the response without guessing.

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 sentences, front-loaded with the meaningful part (what states exist) and ending with the required inputs. Nothing is wasted and the status list directly earns its space.

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?

With no output schema, the description correctly compensates by enumerating the possible status values. It stops short of describing the response shape beyond status (e.g. what fields accompany a confirmed booking) or what happens when the email does not match the booking.

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 description coverage is 100%, and the schema already explains that email proves ownership and bookingId comes from request_booking. The description restates both without adding syntax, format, or edge-case handling, so the schema is doing the heavy lifting.

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 read operation ('Where a booking request stands') on a specific resource and enumerates the possible values it returns. An agent can distinguish it from the mutation siblings (cancel_booking, change_booking) by the read-only framing, but no sibling is named explicitly.

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?

Implies the usage flow by requiring the bookingId from request_booking and the customer's email, which tells the agent this is a post-booking lookup. It gives no explicit exclusions or pointers to alternatives (e.g. when to poll vs. when to use change_booking).

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