cancel_call

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

With no annotations, the description carries the full burden and does so thoroughly: cancelled() flips immediately, a CANCEL_GRACE timeout triggers KeyboardInterrupt in the Inventor thread, the interrupt lands at the next Python line, and calls stuck inside a COM call or modal dialog only stop after that call returns. This is exactly the behavioral nuance an agent needs to set expectations.

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 action is front-loaded in the first clause, and every sentence conveys necessary cancellation semantics. The prose is dense and semicolon-heavy, making it slightly harder to scan than it could be, but there is 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 behaviorally complex cancellation tool with no annotations, the description covers mechanism, grace period, thread behavior, and COM-call limitations. An output schema exists, so return values need not be explained; nothing critical 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%, so the single 'instance' parameter is already documented in the schema. The description adds no syntax or selection guidance beyond what the schema provides, making the baseline 3 appropriate.

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 — 'Stop the running call' — and gives concrete examples (long execute_python loop, Content Center scan, wrong job). This clearly distinguishes it from siblings like call_status and execute_python without needing to open either schema.

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 use cases make it obvious when to invoke cancellation: long-running loops, scans, or erroneous jobs. It even advises polling cancelled() in long loops. However, it never names call_status as the alternative for checking progress, nor states when not to cancel.

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