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

Annotations already establish readOnly, idempotent and non-destructive, so the safety profile is covered. The description adds real substance beyond that: it discloses that step output is trimmed, that workflow runs expose the failed step, and that agent runs surface pending tool approvals, which tells the agent what to expect from a run in a blocked state. It stops short of saying whether log links expire or how large outputs are truncated to.

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?

Two sentences, both dense with content: the first covers scalar results, the second covers the workflow-versus-agent divergence. The opening is a noun fragment rather than a verb phrase, which slightly delays the action, but nothing is padded or redundant.

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?

With no output schema, the description carries the burden of describing return values and does so across both run types, including the less obvious approval and failed-step cases. The remaining gap is minor: cost units, output trimming thresholds, and log link longevity are unspecified, but none of them block a correct call.

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?

There is a single parameter with 100% schema description coverage, so the baseline is 3. The description repeats the schema's dual-id behavior (run_id or request id from the logs) but adds no extra meaning such as format, accepted prefixes, or what happens when an id is stale or from another workspace.

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 names the resource (a workflow or agent run) and concretely enumerates what reading it yields: status, done flag, final output, error, cost, log link, plus step-level and approval details. That is specific enough to distinguish it from write-side siblings like cancel_run or retry_run, though it never explicitly contrasts with get_test_run or diagnose_run, which are the closest read-side alternatives.

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?

Usage is only implied: one infers this is the tool to call after run_workflow, run_agent or list_runs to inspect results, and the request-id note gives a second entry path. There is no explicit when-to-use versus when-not-to-use guidance, and no mention of when diagnose_run or get_test_run would be the better choice.

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