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

Goes well beyond the annotations (destructiveHint/idempotentHint) by disclosing concrete consequences: the slot is released, the payment is reversed, and the refund is full. It also provides a documented failure fallback (email the seller with the order number), which is exactly the kind of operational context annotations cannot convey.

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?

Front-loads purpose and effect in the first sentence, then preconditions, then the fallback. Every sentence carries information, though the fallback sentence is fairly long and slightly dilutes the core instruction.

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 destructive mutation with no output schema, the definition covers preconditions, destructive consequences, and a recovery path. The only meaningful gap is that it never states what the tool returns or how to obtain `order_id`.

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 50%; the `email` description is already documented in the schema as 'Must match the order's email', so the description's repetition adds little. `order_id` remains undocumented in both the schema and the description, so the tool does not compensate for the coverage gap. Baseline 3.

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 verb, resource, and side effect: 'Cancel a booking and refund it in full.' An agent immediately understands the operation. However, sibling `cancel_booking` exists and the description never explains how cancelling an order differs from cancelling a booking, leaving ambiguity between two similarly named tools.

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?

Gives clear preconditions (the email the order was created with) and an explicit call-first instruction ('Confirm with the buyer before calling'). It does not say when to prefer this over `cancel_booking` or `renounce_certificate`, but the usage context for this tool itself is unambiguous.

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