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

Annotations already declare destructiveHint=true and idempotentHint=false, so the bar is lower, but the description still adds real value by explaining what specifically is destroyed (waiting steps) and that nothing further executes. It does not say what happens when the run has already finished or errored, which is the remaining behavioral gap.

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, zero filler, with the effect front-loaded and the irreversibility warning second. Nothing could be removed without losing information.

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 destructive one-shot mutation with no output schema, the definition covers the essential outcome and irreversibility, and annotations carry the safety profile. It falls short only on edge-case behavior (already-completed runs, error responses) and on the purpose of the 'reason' field.

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 67%: id and run_id are documented in the schema, but 'reason' has no description anywhere. The tool description adds no parameter meaning at all, so the undocumented third parameter is left entirely to inference — acceptable but not compensating for the gap.

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 ('Cancel one running run') and defines the effect precisely: waiting steps canceled, no further steps run. It is clearly distinct from cancel-campaign and cancel-email by scope, though it never explicitly contrasts with the automation-level siblings like stop-automation or pause-automation.

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?

There is no guidance on when to choose this over stop-automation, pause-automation, or remove-contact-from-automation, all of which sit in the same sibling set. 'Can't be undone' is a hazard warning, not a usage rule, and no precondition (e.g., the run must still be active) is stated.

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