workflow_control

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

With no annotations, the description carries the full disclosure burden and does real work: it explains that cancellation only stops subsequent steps and that in-flight device/RPC calls either complete or time out first. That is exactly the kind of non-obvious side-effect semantics an agent needs before cancelling. It omits permission/precondition and what identifying a run requires.

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 sentences, zero filler, and the operative distinction (inspect vs cancel) plus the key caveat (in-flight calls finish first) are both front-loaded. Nothing is repeated from structured fields.

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?

Return values are covered by the output schema, and the cancellation semantics are well handled, so the two-sentence length is defensible. But for a tool whose only two parameters have zero schema documentation, the description should still say which action values exist and whether run_id is needed — that gap keeps it at minimum viable.

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% and the description never mentions either parameter. 'action' defaults to 'status' and 'run_id' defaults to null, yet the description gives no indication of valid action values (presumably status vs cancel), whether run_id is required for cancel, or what 'status' returns when run_id is omitted. The description therefore leaves the entire parameter surface undocumented.

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?

Description states a specific pair of verbs (inspect / cooperatively cancel) applied to a specific resource (an active workflow), and the 'from another request' framing separates it from the workflow-launching siblings run_workflow and saved_workflow. It stops short of enumerating the action values that drive the operation, but the core purpose is unambiguous.

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 'from another request' hints at the intended context (out-of-band monitoring/kill from a different session), and 'cooperatively' signals that this is not a hard abort. However, it never states when to prefer this over just letting a workflow finish, nor does it name run_workflow/saved_workflow as the launching counterparts, so the agent must infer the routing.

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