regression_gate

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

With no annotations, the description carries the full burden and it does disclose the core behavior: it invokes run_eval, compares to a baseline, and returns allow/deny. It does not mention side effects, authorization requirements, or edge-case behavior such as equal scores, leaving some behavioral ambiguity.

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 short, front-loaded, and every sentence adds value. It uses two crisp sentences to convey the tool's domain, behavior, and return value without unnecessary 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?

The description provides the essential high-level purpose and return value, but no output schema and sparse parameter guidance leave important gaps for correct invocation. It does not describe the exact response structure or clarify market/vertical semantics, so the overall context is only moderately complete.

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 25%, so the description must compensate, but it only hints at assistantId via "current assistant" and baselineScore via "stored baseline." It does not explain market or vertical, so an agent would not know their intended values or role in the evaluation.

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 states a specific purpose: it runs run_eval against the current assistant, compares against a baseline, and blocks the update on regression. It clearly distinguishes itself from the sibling run_eval by adding the gate/blocking behavior and the allow/deny outcome.

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?

"CI for prompts" immediately establishes the intended context, and the blocking behavior makes it clear this is a gate rather than a plain evaluation tool. However, it does not explicitly mention alternatives, such as using run_eval directly when a non-blocking evaluation is needed.

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