eval.run

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

No annotations are provided, so the description carries the full behavioral burden. It notes that omitting score/pass triggers an AI judge, but says nothing about whether re-submitting overwrites a prior result, what permissions are needed, or what the automated judge_type does. For a mutation-style submit tool this is a substantial gap.

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 tight sentences with the core action front-loaded and no filler. The judging-mode note follows the action in a sensible order. Slightly terse given the unmet parameter and behavioral needs.

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?

Five parameters with low schema coverage and no annotations or output schema, yet the description only addresses the score/pass/judge path. An agent still lacks guidance on judge_type 'automated', submission semantics on repeat calls, and what the call returns, so it is only minimally adequate.

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 only 20%, so the description must compensate and partly does: it explains that score and pass drive manual judging while omitting them delegates to the AI judge, and it names the required eval_case_id/actual_output implicitly. But judge_type's 'automated' value and the exact meaning of score vs pass are left to inference.

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: submit actual output for scoring against an eval case. This clearly separates it from siblings like eval.listCases and eval.listResults, which read rather than submit. It does not explicitly name those siblings, so it stops short of a 5.

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 second sentence gives conditional guidance ('Pass score/pass for manual judging or omit for AI judge'), which is genuinely useful routing between judging modes. However, it never says when to use this tool versus eval.createCase or eval.listResults, so usage versus alternatives is only implied.

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