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

Beyond the annotations, the description reveals important side effects: the failed step reruns, so any request it already sent will be sent again; the failed run remains unchanged and records which run retried it; downstream workflow actions can create, change, or delete records; and runs fail if the key is revoked, expires, or is lowered while waiting. These details are critical for safe invocation and go well beyond what readOnlyHint/destructiveHint alone convey.

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?

The description is front-loaded with the core behavior and side effects, then provides the endpoint and multi-space/permission notes in clearly separated segments. Every sentence adds useful information; there is no filler or redundant restatement.

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 mutating tool with two parameters and no output schema, the description covers behavior, side effects, error conditions, permission requirements, multi-space handling, and downstream execution context. An agent has enough information to invoke it correctly without additional context.

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?

With 50% schema description coverage, the description adds meaning: it identifies runId as the failed run's identifier and explains the multi-space procedure for targetSpaceId (call auth_verify, ask the user, pass targetSpaceId). It could more explicitly state the format or source of runId, but it compensates for the schema gap.

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 specifies exactly what the tool does: it creates a new run that reuses earlier steps unchanged and resumes from the failed step with that step's current settings. This clearly distinguishes it from siblings like workflows_start (new run) and workflows_cancel, letting an agent identify the correct tool without inspecting the schema.

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?

Implicitly, it is for retrying a failed run after a failure, and it lists explicit preconditions and errors (write-level key, 400 if not failed or step gone, 409 if already retried). It does not explicitly name an alternative sibling (e.g., workflows_start for a fresh run), but the failure condition is clear enough to choose correctly.

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