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

Discloses that it is 100% regex-based with zero network calls, which is not covered by annotations. Annotations already declare readOnlyHint=true and destructiveHint=false, but description adds that it's regex-based (not ML) and doesn't exfiltrate data—critical for trust. No contradiction.

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?

Two sentences, no fluff, front-loaded with purpose. Every word contributes: listing secret types, return info, usage timing, and behavioral caveat. Perfectly sized for quick understanding.

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 simple input (string) and optional types, plus output schema exists, the description fully covers what's needed: return format, usage timing, and safety behavior. No gaps for an agent to misuse the tool.

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% with descriptions, but description adds detail on the 'types' parameter: lists default 'all' and gives examples (e.g., 'aws_access_key'), and notes that unknown values are rejected. This goes beyond schema by clarifying behavior on invalid input.

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?

Clearly states it scans text/code for leaked secrets, lists specific types (API keys, private keys, JWTs, etc.) and return findings. Distinguishes from sibling 'detect_secrets' by specifying the comprehensive families and usage context, making it the go-to secret scanner.

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 instructs when to use: before committing code, sharing logs, or sending text to an LLM. This clearly delineates use cases and suggests this is the recommended tool for secret scanning, differentiating from siblings like 'detect_secrets' and 'redact_pii'.

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