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

Goes well beyond the read-only/idempotent annotations: it details the error object shape (code, providerStatus, message, requestId, whoseError, retryable, retryHint), guarantees no secrets or raw provider headers, explains the optional 'normalized' block, and clarifies that fields/max_items return a trimmed copy with unchanged charge and that unknown paths error. Rich disclosure an agent could not get from structured fields.

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-loads the core purpose and is information-dense, but the single long block with internal ticket codes (CA-WF-02/CA-WF-08) and heavy parentheticals slightly hurts scanability. Most sentences still earn their 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?

No output schema exists, so the description carries return-value burden and does so thoroughly: status vs provider status, result, cost, error shape, normalized block, and media/downloadUrl semantics. Nothing an agent needs to call it correctly is missing.

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 0% schema description coverage, the description compensates by explaining that `fields` are dotted paths of the result to keep and `max_items` caps every list, plus the edge case that a nonexistent path is an error. It adds real meaning beyond the bare schema, though the maxItems:50 cap and runId semantics rely on the schema/obviousness.

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 run') and immediately scopes it: returns lifecycle status distinct from the provider's own response status, plus result and cost once settled. It clearly differentiates itself from siblings like runs_list and runs_cancel by describing what a single-run fetch returns.

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?

It gives useful situational context (following a workflow run started via run() with endpointId 'workflow:<id>', by workflowRunId) but never explicitly states when to use this over runs_list, runs_evidence, or runs_cancel. Usage is implied rather than articulated.

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