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

Annotations already declare destructiveHint=true and readOnlyHint=false, so the safety profile is covered; the description earns credit for adding what the annotations cannot: the cancel is a cooperative request ('asks... to stop') rather than a guaranteed kill, and already-found results are retained. It still omits whether cancel is idempotent, whether a completed run errors, and how long the wind-down takes.

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, and the core behavior plus the most important consequence (results are preserved) are front-loaded.

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 single-parameter mutation whose annotations already flag destructiveness and whose return value is unspecified, the description covers the essentials but leaves an agent guessing about post-cancel state, idempotency, and how to retrieve the retained results (presumably get_find).

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?

There is one parameter, find_id, with 0% schema description coverage and no mention in the description. The 'run in progress' phrasing implies the id must reference an active run, but the description adds no format, sourcing, or error semantics beyond that inference.

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 — asking a run in progress to stop — which maps cleanly to cancel_find and is distinguishable from cancel_investigation_batch. It never actually uses the name 'find', so the link relies on the tool name and the find_id parameter rather than the prose.

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 phrase 'a run in progress' implicitly scopes usage to active runs, which is useful context. However, it gives no explicit when/when-not guidance, no alternatives (e.g., a cancel_investigation_batch sibling for batch-level cancellations), and says nothing about what happens if the run already completed.

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