Cancel Order

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

Beyond the annotations (readOnlyHint=false, destructiveHint=true, idempotentHint=true), the description discloses crucial behavioral traits: dry-run-vs-execute semantics, the mandatory two-step confirmation flow, the code being derived from and bound to the exact order, the single-use nature, the never-quote-back rule, and the return format. This substantially enriches what the annotations alone convey and aligns with them — no contradiction with destructiveHint=true or idempotentHint=true.

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?

The description is longer than average but the length is justified for a destructive tool with a mandatory confirmation flow. It is front-loaded with purpose and return behavior before diving into the safety protocol. Minor redundancy exists ("derived from the order" and "applies only to that exact order" say nearly the same thing; "never in the same turn the user first asks" partially overlaps with "after the user has explicitly confirmed"), but no sentence is wasted.

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 high-complexity destructive tool with no output schema, the description covers everything an agent needs: success return value, error conditions, the exact call sequence, the confirmation-code constraints, and how the user can verify the targeted order. Nothing essential for correct invocation 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 description coverage is 100%, and the schema's execute parameter already documents the full confirmation protocol including 10-minute expiry and single-use behavior. The description reinforces this content but does not meaningfully add beyond the structured schema, so the 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?

The description opens with a specific verb+resource statement — "Cancel an open order by order_id" — that precisely identifies the action, the target, and the required identifier. The scope (open orders only) plus the error-on-filled/cancelled clause clearly differentiates it from siblings like submit_order, replace_order, and grid_cancel without needing to name them.

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?

The description provides unusually explicit procedural guidance: call once without execute for a dry run, show the preview to the user, then call again with execute only after explicit confirmation. The "errors if the order is already filled or cancelled" clause is an implicit when-not condition. However, no sibling alternatives are explicitly named (e.g., pointing to replace_order when modification rather than cancellation is wanted), so it stops just short of a 5.

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