cancel

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

With no annotations, the description carries the full burden and does deliver real behavioral context: the order must be untouched, the operation is protected and disabled by default, and the SDK uses the order's own recorded reservation remainder rather than the caller's value. It stops short of stating what happens to holds/reservations on success, what errors arise on a touched order, or the auth requirements behind 'protected'.

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 core purpose is front-loaded, but the body is a single dense run-on of internal terminology ('signed hold approval Officer', 'SDK receives the order's own recorded reservation remainder') that requires re-reading. The important gating fact, 'Protected and disabled by default', is buried in the final clause instead of being surfaced early.

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 3-parameter mutation tool with no annotations, the description covers preconditions, the confusing leavesQuantity semantics, and the availability gate, and an output schema exists so return values need not be explained. It leaves gaps on failure modes for non-untouched orders and on what 'protected' requires operationally, but an agent has enough to decide whether to call it.

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%, so all three parameters are already documented — and the schema text for leavesQuantity is nearly verbatim the description text, so little new meaning is added. The description does clarify the caller-reported vs SDK-recorded distinction, but that same clarification already appears in the 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?

States a specific verb ('Cancel') and resource ('workflow order') plus a precondition ('untouched') that separates it from check_order/confirm_execution/report_fill siblings. The qualifier 'from the signed hold approval Officer recorded at submit' is domain jargon that an unfamiliar agent cannot decode, so the purpose is clear but the scope is not fully self-explanatory.

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?

'Cancel an untouched ... order' implies the when (order exists but has not been touched), and 'After execution-report activity, submit an explicit report' implies a boundary with report_fill, but neither names a sibling tool nor states an explicit exclusion. 'Protected and disabled by default' hints at an availability gate without explaining how to satisfy it. Usage is inferable but not directed.

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