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

Annotations already declare destructiveHint=true and idempotentHint=true, so the safety profile is structured. The description still adds meaningful context beyond them: cancellation is scoped to 'one' run and 'existing results remain available for inspection,' which tells the agent precisely what is and isn't destroyed — the key uncertainty for a destructive tool.

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 with zero filler; the actor constraint comes first and the post-condition reassurance second. Every clause carries information an agent needs.

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?

With full schema coverage, an output schema, and rich annotations, the description only needs to supply purpose, guardrail, and aftermath — all of which it does. A minor gap remains around edge cases such as cancelling an already-terminal or non-existent run, and whether an error or a no-op results.

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% and both parameters (run_id with its UUID pattern, organization_id with its list_organizations guidance) are documented in the schema. The description adds no syntax, format, or selection guidance beyond that, so the baseline of 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?

The description uses a specific verb ('Cancel') and a specific resource ('one durable analysis run'), and the word 'durable' plus 'run' separates it from sibling tools like cancel_research_deliverable or cancel_feasibility_request. It stops short of explicitly naming which sibling handles cancellation of other artifact types, so the differentiation is inferential rather than stated.

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?

'Only when the user requests it' is a real usage constraint that steers the agent away from speculative cancellation. However, no alternatives are named and no when-not conditions are given — nothing tells the agent what to do instead if the run is already complete, failed, or needs resumption (e.g., resume_research_analysis).

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