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

Annotations declare destructiveHint=true and readOnlyHint=false, and the description goes well beyond that: it specifies that no further step starts, that a running command is stopped while a running file step or copy completes first, and that completed steps are not rolled back. This granular cancellation semantics and irreversibility disclosure is exactly the extra context annotations cannot carry.

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?

Four short sentences, front-loaded with the action and target, then the behavioral caveats, then the follow-up instruction. No filler and every sentence carries decision-relevant information.

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?

No output schema exists, so the description must cover outcomes — and it does via the 'poll workflow_status until cancelled' instruction, plus the per-step cancellation behavior. It omits edge cases such as what happens if the run has already finished or failed, which keeps it short of fully complete.

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 coverage is 67%: deviceId and workSessionId are already documented in the schema, while runId has no schema description. The description only says 'by runId' and 'in the same work session', which adds minimal meaning beyond what the schema properties already convey. Baseline 3 is appropriate when the schema does most of 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 (workflow run) plus identifier (runId) and session scoping ('in the same work session'). An agent can immediately separate this from siblings like delete_workflow (definition removal), run_workflow, or workflow_status.

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?

Gives clear context for use (a running workflow run) and names the follow-up action to take — 'Poll workflow_status until the state is cancelled' — which routes the agent to the correct next tool. It does not, however, state when not to use it (e.g. vs delete_workflow for a non-running workflow), so exclusions are left implicit.

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