CIS Benchmark

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

The description explicitly states 'All checks are read-only,' which aligns with the readOnlyHint annotation. It additionally discloses credential requirements and the inclusion of MITRE ATT&CK mappings, providing useful behavioral context beyond the annotations. No contradiction is 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?

The description is structured with a clear lead sentence followed by a bullet-like enumeration of benchmarks and a return format section. It is informative without excessive verbosity, though the list of check counts could be seen as slightly extraneous.

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 a comprehensive overview of the tool's purpose, the benchmarks it covers, the output format (JSON with pass/fail, evidence, severity, ATT&CK techniques, pass rate), and prerequisites. This is sufficient for an agent to understand expectations without an explicit output schema.

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 already covers each parameter with clear descriptions (e.g., provider values, env var fallbacks, check ID format). The description's top-level text does not add significant new parameter information beyond the schema, so it does not exceed the baseline of 3.

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 'Run CIS benchmark checks against a cloud account' with a specific verb and resource. It distinguishes from sibling tools like 'compliance' or 'policy_check' by explicitly naming CIS Foundations Benchmarks and enumerating provider-specific check counts.

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?

It states when to use (for CIS benchmark evaluation) and implicitly differentiates from generic compliance checks. It also notes that 'appropriate credentials' are required, which is a prerequisite. It doesn't explicitly list alternatives, but the specificity is sufficient.

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