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

Annotations already declare readOnlyHint, idempotentHint and destructiveHint=false, so the safety profile is covered. The description adds real behavioral context beyond that: what the response contains and the pagination behavior ('50 steps by default and 200 at most'), which is useful for interpreting truncated traces.

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?

Three tight sentences. The use-case trigger is front-loaded, the return payload follows, and the exclusion closes it. No filler.

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?

An output schema exists, so return values need not be fully enumerated, yet the description still summarizes them and notes the step cap. For a read-only trace tool with two required ids, nothing an agent needs to invoke 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?

Schema description coverage is 100%, so runId, projectId and stepLimit are all already documented in the schema, including the same 1-200/default-50 range repeated in the description. Baseline 3 applies; the description adds no new parameter meaning.

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?

Specific verb and resource: it traces a workflow run and states exactly what comes back — run status, timings, error code, plus steps with status, attempt, timings and error code. It also distinguishes itself from the listing sibling with 'Not for listing runs.'

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?

Gives an explicit trigger ('when someone asks why a durable workflow run failed or where it is stuck') and an explicit exclusion ('Not for listing runs'), which routes the agent away from list_workflow_runs.

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