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

Annotations only declare the safe read profile; the description adds non-obvious runtime behavior the annotations cannot convey — that a run can be paused on a manual gate, that repeated polling is futile in that state, and that a human decision plus specific revision/digest fields are prerequisites. That is exactly the kind of state-machine context an agent needs before acting.

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?

Front-loaded with the core purpose in the first clause, and the second sentence, while long, is dense with decision-relevant detail rather than filler. It is slightly heavy for a two-parameter read tool but every clause earns its place.

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 carries the return-value burden and does name the key surfaces (status, progress, node results, requiredAction). It stops short of enumerating the full response shape or what a terminal-state run looks like, leaving a small gap for an agent parsing results.

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 100%, and both run_id and organization_id already carry provenance notes in the schema ('returned by start_workflow or list_workflow_runs', 'returned by list_organizations'), so the description's 'one known workflow run ID' is largely redundant. The expectedRevision/approvalDigest/afterWave/gateIndex references belong to the response object, not this tool's inputs, so they don't deepen input semantics.

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?

States a specific verb and resource (get a single workflow run) and enumerates what it returns: status, progress, and node results. It also explicitly distinguishes itself from list_workflow_runs, so the agent can pick the right tool without opening either 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?

Names the alternative for discovery ('use list_workflow_runs to discover runs') and gives an explicit conditional branch: when requiredAction.type is 'approval', polling will not resolve it and approve_workflow_step must be called with the user's explicit decision. This is a genuine when/when-not/alternative routing instruction.

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