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 carried by structured data. The description adds value by disclosing that only queued/running runs are affected and finished runs are left alone, but it says nothing about whether cancellation is reversible, what happens to partial output, or required permissions.

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 no waste; the eligible-state condition is front-loaded and the edge case follows immediately. Nothing could be cut without losing meaning.

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?

There is no output schema, so the description is the only place to learn what a cancel returns, and it stays silent. Combined with zero schema description coverage on three required parameters, including the mandatory idempotency key, an agent is missing information it needs to invoke this mutation correctly.

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 0% across three required parameters, and the description compensates for none of them. The required idempotency_key in particular is never explained (retry semantics, replay behavior), and the workspace/run scoping is left entirely to the schema's names and formats.

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 gives a specific verb (stop) and resource (a queued or running teammate or operator run), which clearly separates it from agent_runs_get, agent_runs_list and agent_runs_start. It never names the other cancel tools (jobs_cancel, publish_cancel), but those operate on different resources, so confusion risk is low.

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 'queued or running' implies the precondition for calling it, and 'Finished runs are unchanged' tells the agent what happens if the state is wrong. No explicit exclusions, prerequisites, or alternative tools are mentioned, so usage is only implied.

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