cancel_run

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

With no annotations, the description carries the full behavioral burden. It does disclose the key trait that the action is irreversible, which is genuinely useful, but omits permissions required, what happens to in-flight output on cancel, and whether the run must be in a cancellable state.

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 short sentences, front-loaded with the action and followed by the risk. No filler, though 'a specific' is slightly redundant for a single-run tool.

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 one-parameter mutation with no annotations and no output schema, disclosing irreversibility covers the most important gap. The remaining omission — how this relates to create_cancellation and when each should be used — leaves the definition only minimally complete.

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?

Only one parameter (runId) with 100% schema description coverage ('The run ID (ULID) to cancel'), so the schema already carries the semantics. The description adds nothing about the identifier beyond what's in the schema, which is the expected baseline here.

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 ('function run'), which is enough for an agent to know what the tool does. However, it never differentiates from the sibling create_cancellation, which plausibly overlaps in intent, so the agent must open both schemas to tell them apart.

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?

'Use with caution' is a risk warning, not usage guidance — it says nothing about when to call this versus create_cancellation or the other cancellation-adjacent siblings. No prerequisites, no preconditions (e.g., run must be in progress), and no exclusions are given.

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