evaluate_policy

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

Without annotations, the description does well to disclose key behaviors: it runs all scanners, evaluates against a policy, returns a verdict, explains the -1 threshold semantics, and the interaction between 'fail_on_new' and baseline. It does not mention side effects (e.g., data mutation) or authentication requirements, but given the read-only nature implied, it is transparent enough.

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 three sentences long, front-loaded with the core purpose and outcome. Each sentence contributes unique information: first the general action and result, second the threshold semantics, third the special fail_on_new behavior. No redundant or irrelevant content.

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?

Given the context signals (9 parameters, 100% coverage, output schema exists), the description is sufficiently complete. It explains the return format (PASS/FAIL), the threshold mechanism, and the baseline condition. Some edge cases (e.g., what if no scanners are enabled?) are not covered, but the overall picture is adequate for selection and invocation.

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 parameters have individual descriptions. The description adds value by explaining the -1 threshold meaning and the condition when 'fail_on_new' causes failure relative to a baseline. This connects parameters like 'fail_on_new' and 'baseline_tag' beyond what the schema provides individually.

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 clearly states the tool runs all scanners and evaluates findings against a CI security policy, returning an explicit PASS/FAIL verdict for pipeline gating. It uses specific verbs ('run', 'evaluate') and identifies the resource ('scanners', 'CI security policy'). It distinguishes from sibling tools like 'scan_all' which only scans or 'compliance_report' which likely just generates reports.

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 mentions the threshold behavior ('-1 means no limit') and the 'fail_on_new' option with baseline reference. However, it does not explicitly state when to use this tool versus alternatives like 'scan_all' or 'compliance_report', nor does it provide context on when not to use it. The mention of 'save_baseline' is a cross-reference but not a usage guideline.

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