scan_secrets

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

Annotations are absent, so the description carries the burden. It discloses the scanning process (using gitleaks/trufflehog) and the type of files it scans (directory or file). However, it does not mention any potential side effects (e.g., whether it modifies files, default permissions, or rate limits). It is a scanning tool, so destructive behavior is unlikely, but the description does not explicitly state it is read-only or what safety guarantees exist.

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 very concise: two sentences contain useful information without redundancy. It is front-loaded with the main purpose and then adds the tool choice detail. No fluff or unnecessary explanation. Optimally sized for quick reading.

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 presence of an output schema, the description does not need to detail return values. It sufficiently covers the operation scope (filesystem path, backend selection) and the purpose (finding secrets). The description avoids overwhelming detail while providing enough context for the agent to understand what the tool does and when to invoke it. The lack of side-effect or usage limitations is covered under behavioural aspects, but overall it's adequately complete for a scanning 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?

The schema description coverage is 100%, and parameters like 'path' (directory or file) and 'backend' (gitleaks/trufflehog) are already thoroughly described. The tool description adds meaning by stating the goal (detecting leaked secrets) and that it handles 'hardcoded secrets, API keys, tokens, and credentials', but it does not provide deeper insight into the parameters beyond the schema. Since the schema already has solid descriptions, the description adds little marginal value, resulting in a baseline of 3, but the slight extra context about file scanning type and credential types justifies a 4.

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 scans a filesystem path for leaked secrets, using gitleaks or trufflehog. It specifies the verb (scan) and resource (filesystem path), and mentions the types of secrets (API keys, tokens, credentials). However, it does not explicitly differentiate itself from the sibling tool 'scan_git_secrets', though the 'filesystem path' phrasing implies a broader scope vs. git-specific scanning.

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 clearly indicates when to use the tool: to scan a directory or file for secrets. It doesn't explicitly mention alternatives, but the description's focus on filesystem paths and the existence of 'scan_git_secrets' implies it's for non-git scans. The context is clear enough, but without an explicit 'when-not-to-use' or 'use this tool when...' statement, it falls short of a 5.

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