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

Strong beyond-annotation content: write-level key requirement, the run acts as the key's owner but capped by key permissions, revocation/expiry/downgrade while paused fails the run, and runs can call webhooks/functions and modify records. The only friction is that destructiveHint=false while the text says a run can "delete records" — an indirect effect, not a direct contradiction, but an agent could read it as more destructive than the annotation suggests.

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?

Mis-front-loaded: the opening sentence explains the post-call state instead of the action, and the HTTP endpoint is wedged mid-paragraph. Ideas repeat — "It keeps acting as the key's owner, capped by the key" and "It acts as this key's owner but never beyond this key's permission level" say the same thing twice.

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?

The description covers auth, side effects, failure-on-revocation semantics, and partially the resulting states, which is decent for a mutating tool with no output schema. It is still incomplete on how payload, recordId, and eventName shape the run — the very inputs an agent must supply.

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 only 20%, so the description must compensate — it doesn't. Four of five parameters (nodeId, payload, recordId, eventName) get no meaning, format, or interaction explanation anywhere; only targetSpaceId is addressed, and that merely restates the schema's own description.

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 action is never stated cleanly up front — the first sentence describes the resulting state ("The run as it stands after its first steps: completed, failed, or paused") rather than "starts a workflow run." The verb only surfaces obliquely near the end ("Start a run only when the user asks for it") and nothing distinguishes it from siblings like workflows_cancel, workflows_decide, or workflows_get.

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?

There is real guidance: "Start a run only when the user asks for it" acts as an explicit gate, and the multi-space branch tells the agent to call auth_verify and pass targetSpaceId. However, no alternative tool is named, so the agent gets no routing help versus workflows_cancel/workflows_decide or versus reading a run with workflows_get.

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