Generate security audit

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

Beyond annotations (readOnly, idempotent, non-destructive), the description adds behavioral context: "makes exactly one POST /audit request," "safe to retry but remains unsafe-mode and owner-authorized," and "Returns a sanitized, untrusted report; a clean scan returns an empty map." This enriches the agent's understanding of security, side effects, and failure behavior.

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?

Despite being relatively long, every sentence adds value: purpose, parameter usage, side effects, safety, alternatives, return behavior, and retry guidance. It is front-loaded with the main purpose and maintains a clear logical flow. No filler or redundancy.

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 tool's simplicity (one optional parameter) and the rich annotations plus an output schema, the description goes beyond what is necessary by covering authorization, sensitivity, return format, and failure mitigation. It is fully complete for an agent to invoke correctly.

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 fully describes the categories parameter (1-5 unique items, optional, default selection). The description adds one important constraint beyond the schema: "an empty array is rejected." This is a meaningful behavioral detail, but most parameter semantics are already in the schema, so the description's incremental value is limited to that rejection rule.

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 opens with a specific verb and resource: "Run one read-only n8n security scan." It clearly distinguishes itself from siblings by mentioning an alternative for single-workflow inspection ("Use n8n_introspect for one workflow"). This makes the purpose unambiguous and differentiated.

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?

Provides explicit usage context: when to omit categories for a default scan, accepts 1-5 categories, and rejects empty arrays. It also names an alternative tool (n8n_introspect) for a different use case and gives retry advice if the report cannot fit, which serves as clear when-to-use and troubleshooting guidance.

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