cancel_run

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

With no annotations, the description fully covers behavioral traits: stops further steps and clarifies that completed steps and side effects are not undone. This is good transparency, though it could mention required permissions or idempotency.

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?

Two sentences, front-loaded with the primary action, no fluff. Every word adds value.

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?

Given a simple 1-param tool with no output schema, the description is nearly complete. It covers action, effect on uncompleted steps, and the non-reversibility of completed steps. Missing: error handling (e.g., if run not found or already completed) and whether the operation is idempotent.

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% with runId described. The description adds meaningful context by specifying the run must be 'in-flight', which is beyond the schema's trivial description. This helps the agent provide the correct run state.

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 clearly states the action 'cancel' on the resource 'run' (in-flight). It distinguishes from siblings like 'delete_run' by noting that completed steps are not undone, making the purpose specific and unambiguous.

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 implies usage when the run is 'in-flight', but does not explicitly exclude other states (e.g., already completed) or provide alternative tools like 'delete_run' or 'archive_run'. No when-not-to-use guidance.

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