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

Goes beyond the annotations ('destructiveHint: false', 'idempotentHint: true') by disclosing that a human reviews the request, that production may already have started so cancellation is not guaranteed, and the specific retry quirk where re-asking within 24 hours only amends the reason without a second notification. It does not cover auth or permission requirements.

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?

Three compact sentences, front-loaded with the action and its precondition, then the review/uncertainty caveat, then retry semantics and where to observe the result. No filler.

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 mutating request tool with an output schema present, the description supplies everything else an agent needs: the eligibility condition, that fulfillment is human-mediated and may fail, idempotency behavior on retry, and where to read the outcome. Nothing material is missing.

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 100% and both parameters (order_id, reason) are documented in the schema, including the ord_... format and that the reason is for the reviewer. The description adds no further parameter detail, so baseline 3 applies.

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 and resource ('Ask the shop to cancel an order') and immediately scopes it with 'that hasn't shipped', which separates it from the read-side siblings get_order and list_orders. An agent knows this is a request/negotiation action, not an immediate destructive cancel.

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 the operative condition ('hasn't shipped') and points to the outcome path (order.status_changed webhook, get_order). It also covers the repeat-call case explicitly, though it never states the inverse condition (what to do if the order has shipped) or names a distinct alternative tool.

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