gate_evals

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

With no annotations, the description carries the full behavioral burden and largely fails: it does not say whether this is a read or a compute/trigger operation, whether it requires a prior run or baseline, or what 'trusted' means as a returned signal. It does hint at the shape of the result (per-provider counts plus a trust flag), which is the only behavioral content present.

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?

It is short, but this is under-specification rather than concision: a single elliptical fragment with a colon-led field list and no subject, verb, or front-loaded statement of function. Every word is terse but the sentence does not earn its place as a complete tool definition.

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 no annotations, no output schema, and no parameters, the description is the only carrier of meaning, and it omits whether the tool runs or reads evals, what 'trusted' gates, and how results relate to gate_verdict/baseline. For a tool in a dense gate_* family, that is insufficient.

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 has zero parameters, so per the rubric the baseline is 4. There is nothing for the description to clarify, and it does not misdescribe any input.

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 fragment names a resource area ('each provider's eval') and enumerates three output fields (faults caught, good cases passed, trusted), so an agent can guess this surfaces per-provider eval outcomes. But there is no verb — it never says whether it reads stored results, triggers an evaluation, or summarizes a prior run — leaving the purpose vague against siblings like gate_cases, gate_metrics, gate_run and gate_verdict.

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?

No when-to-use guidance at all: nothing states when to call gate_evals rather than gate_run, gate_metrics, or gate_verdict, and no prerequisites or exclusions are given. The agent must infer the routing from the name alone.

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