audit_manifests

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

Annotations already declare readOnlyHint, idempotentHint, and destructiveHint, so the safety profile is covered. The description adds valuable behavioral details: results are sorted by severity, and secret values are never echoed back. These go beyond the annotations and reassure the agent about output handling and security.

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 compact and well-organized: a one-line purpose, followed by parameter explanations, then output behavior. Every sentence adds useful information, and the most important scoping detail (trap subset selection) is clearly presented. There is no filler or repetition of schema fields.

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?

For a two-parameter read-only tool, the description covers input format, optional filtering, default behavior, output ordering, and a security guarantee. Without an output schema, slightly more detail about the shape of findings could help, but the sibling tools list_traps and explain_trap fill the surrounding context, and nothing essential is missing for correct 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 description coverage is 0%, so the description carries full responsibility for parameter meaning. It clearly explains that manifests is one or more YAML strings and explicitly supports multi-document and helm template formats. It also clarifies that traps is an optional subset of trap IDs, with an example and the default-all behavior. Both parameters are meaningfully enriched.

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 verb and resource: 'Check Kubernetes YAML for known production traps.' This clearly distinguishes the tool from siblings list_traps and explain_trap, which list and explain traps rather than auditing manifests. The function's scope, checking production-relevant pitfalls, is immediately understandable.

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 gives practical usage context: manifests can be multi-document YAML and helm template output works, and traps can be restricted to a subset or left to run all. It does not explicitly state when to prefer this tool over list_traps or explain_trap, but the verb and resource make the intended use clear enough without requiring exclusions.

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