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

Annotations already declare destructive=true and idempotent=true, but the description adds the non-obvious asynchronous semantics: a stop signal that only takes effect after the current processing step completes. It also pre-empts a likely false alarm (a queued node is waiting its turn, not stuck), which is exactly the behavioral context an agent cannot get from structured fields.

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?

Three tight sentences, front-loaded with the action, followed by the mechanism, the verification path, and one caveat. No sentence is redundant.

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, no-output-schema cancellation tool, the description covers trigger, effect timing, verification, and a common misread. Nothing an agent needs in order to call it correctly is missing.

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?

One parameter with 100% schema description coverage, so the schema already explains flow_id fully. The description adds no format, sourcing, or validity detail beyond it, which is the expected baseline when the schema does the work.

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?

Specific verb ('Cancel') plus resource ('a currently running flow'), and the 'currently running' qualifier scopes it away from permanent removal tools like delete_flow. It does not explicitly name or contrast any sibling, so it is clear but not fully differentiated in-text.

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?

It routes the agent to a sibling for the follow-up task ('Use get_flow(view="status") to confirm it has stopped') and gives a concrete when-not-to-act warning about nodes in wait.phase "queued". It never states when to prefer cancel over delete_flow or edit_flow, so it falls short of explicit alternatives/exclusions.

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