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

Annotations already declare destructiveHint=true, idempotentHint=true, and openWorldHint=true, so the safety and idempotency profile is covered. The description adds material business context beyond that: cancellation is only valid before preparation, requires explicit user approval, and does not itself handle refunds. It does not explain grant_id or idempotency_key behavior.

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?

A single compact sentence front-loads the action and its key constraint with no filler. Every clause carries operational meaning.

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 destructive, open-world mutation with four parameters and no output schema, the description covers the most important business precondition but leaves significant gaps around grant_id, idempotency semantics, and what cancellation actually does to the order. It is adequate for avoiding the worst misuse but not complete.

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 0%, so the description must compensate, but it only indirectly explains the approved parameter through 'explicit user approval'. It says nothing about order_id, grant_id, or idempotency_key, leaving three of four parameters undocumented in both schema and description.

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 states a specific action (cancel) and constrains it to before preparation, which clearly distinguishes it from post-preparation flows and refund handling. It does not explicitly name the resource 'order', but the tool name supplies that, and the sibling set lacks a competing cancel tool.

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 a clear when-to-use rule (only before preparation) and a required precondition (explicit user approval). It also notes that refunds are tracked separately, which helps avoid conflating cancellation with refund workflows, though it does not name the specific sibling tool to use for refunds.

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