read_run

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

With no annotations provided, the description carries the full burden. It explicitly lists the output components, including the note about verdicts being the closest to evaluator findings. It does not disclose behavioral traits like authentication needs or performance characteristics, but the read nature is clear.

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 a single, well-front-loaded sentence that efficiently lists all components. It could be slightly more structured (e.g., a bullet list), but it is concise and effective without fluff.

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 one-parameter read tool without output schema, the description fully explains the return values, covering all major components. The clarification about verdicts and the absence of a separate findings endpoint adds completeness. No additional details are necessary given the tool's simplicity.

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% for the single parameter (runId). The description does not add meaning beyond the schema; it just states the tool's purpose. Baseline 3 is appropriate as the schema already documents the parameter adequately.

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 reads one full run and enumerates all components returned (status, per-step state, workflow snapshot, trigger input, agent invocations, validator verdicts). It distinguishes from sibling tools like read_run_trace and read_run_cost by specifying the comprehensive nature of this read. The mention of verdicts as closest to evaluator findings further clarifies its unique value.

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 implies usage (when you need full run details) but does not explicitly state when to use this vs alternatives like read_run_trace or read_run_cost. It hints that there is no separate findings endpoint, suggesting this is the only way to get verdicts, but lacks explicit when-not-to-use guidance.

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