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

Beyond the annotations, the description discloses specific behavioral details: live endpoint serve runs store only the first few KB, runs triggered via run_workflow/preview store full output, and the output is decoded as a string with an output_truncated flag. This significantly enhances transparency.

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 concise, with three sentences each adding value: the main purpose, truncation behavior for live endpoint runs, and full storage for triggered runs. No redundant or extraneous information.

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 tool with a single parameter and an output schema, the description covers the purpose, returned fields, and important caveats about output truncation. It is sufficiently complete for an agent to decide when and how to use it.

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?

The schema already describes run_id as 'the run id returned by run_workflow', and the description adds no further parameter details. With 100% schema coverage, the baseline score of 3 is appropriate.

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 clearly states the tool retrieves a stored workflow run by run ID and lists the key fields returned (status, content_type, output). It distinguishes this from sibling list/get tools by focusing on past run records.

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?

The description provides usage context by explaining that runs from live endpoint serves have truncated output and suggests re-running or previewing to get full output. This gives some guidance on when alternatives might be more appropriate, though it does not explicitly compare with list_runs or other run-related getters.

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