list_evaluation_run_results

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

With no annotations the description carries the full behavioral burden, and it does substantial work: it enumerates the status values (passed/failed/error/scored), explains that turns are truncated to 300 chars rather than dropped and why, and states that paging is page-numbered with page_size capped at 100. It stops short of permission requirements, ordering behavior, or response shape, which keeps it out of the top band.

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 purpose is front-loaded in the first clause, followed by status values and then the truncation caveat; every sentence carries information. The truncation sentence is slightly long but the added detail (why turns are kept) is genuinely useful rather than 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?

For a paginated list tool with no annotations and no output schema, the description covers the agent's main risks: documented status values, the truncation trade-off, the absence of a detail endpoint, and the pagination ceiling. Only the undefined `order` parameter leaves a real gap.

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 0%, so the description must compensate for all four parameters. It clarifies page_size (capped at 100) and that results are page-numbered, but says nothing about the `order` parameter's accepted values or about evaluation_run_id's format, leaving two parameters semantically undocumented.

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 ('List one run's per-prompt results') and enumerates the returned fields (score, status, conversation transcript). It is clearly distinguishable from the sibling get_evaluation_run (run-level) and get_finding_detail without opening any schema.

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 a clear routing condition: there is no per-result detail endpoint, so this is the only way to get the transcript, and for full-fidelity review the agent should use the product UI instead. It does not explicitly contrast with get_evaluation_run or state when NOT to list results (e.g., vs. get_agent_evaluation_summary), but the primary use case and its limitation are well signposted.

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