red_flag_check

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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive), and the description adds substantial context beyond them: RED sets deploy_blocked, the returned diagnostics (components, contributions, reasons, violations, missing measures, coverage needed for GREEN), and the fact that missing evidence lowers coverage rather than being imputed. It also discloses a hard environmental prerequisite (Stochastly running with an Atelier or Portfolio licence).

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?

Front-loads the deployment verdict and the null-handling rule, and every substantive sentence earns its place. However, the install prerequisite is spread over three sentences up front and then partially repeated at the end ('Needs Stochastly open with an Atelier or Portfolio licence'), a redundancy that costs conciseness.

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?

There is no output schema, so the description carries the return-value burden, and it does: verdict, score, per-component contributions, reasons, violation codes, missing measures, and GREEN coverage requirements. Combined with the prerequisite and sibling routing, an agent has everything needed to call and interpret it.

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 coverage is 100%, so the baseline is 3, but the description adds genuine semantics: null is a meaningful 'not measured' value that reduces coverage instead of being guessed, which tells the agent how to populate the five required fields. It does not add units, ranges, or thresholds per measure.

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+resource: combines five overfitting measures into one deployment verdict (GREEN/AMBER/RED) with a 0-100 score. It also enumerates the returned artifacts, so an agent knows exactly what the tool produces without opening a 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?

Explicitly says 'Use it to decide whether a configuration or run is fit to deploy' and routes adjacent needs to named siblings: diagnostic_explain for explaining a violation code, adversarial_check for refuting a finished run. The null-for-unmeasured rule gives a clear invocation condition.

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