Rank eval results

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

Annotations already establish readOnly, idempotent, non-destructive, closed-world behavior, lowering the bar. The description usefully discloses that it computes rankings, a cost/reliability cascade, and dropped dominated models, but says nothing about handling of malformed input, missing threshold, or failure modes.

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?

A single dense sentence that front-loads the primary output (cheapest passing model) and then appends the secondary artifacts. Efficient, though the clause stacking makes it slightly heavy.

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?

With an output schema present and full annotation coverage, the description need not restate return structure, yet it still characterizes the result meaningfully. It is complete enough to call correctly, with only usage-context guidance 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 both 'results' and the 'response_format' enum are already fully documented in the schema; the description merely echoes that it reads a results.json object. Baseline 3 is appropriate since the schema carries the 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?

States a precise verb ('Read') and resource ('results.json object') and spells out the exact return: the cheapest model meeting the pass threshold, ranked by cost per passing call, plus the cascade and dominated models. An agent can distinguish this ranking/analysis tool from siblings like estimate_cost or generate_routing 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?

The description implies its place in the workflow (consume a results.json written by eval_models.py), but it never states when to reach for this versus alternatives, nor any prerequisites or exclusions. Usage is only inferred from the input/output description.

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