security_scan_secrets

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

No annotations are provided, so the description carries the full burden of behavioral disclosure. It does add one useful behavioral trait — the scan is limited to 'text files' (excluding binary artifacts). However, it never explicitly confirms a read-only, non-destructive operation, which is material given the destructive sibling security_auto_sanitize_secrets, nor does it disclose limits such as file-type filters, symlink handling, or performance on large repos.

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?

One tight sentence with zero filler; the action verb leads, and the specific secret types are enumerated efficiently. Every token earns its place.

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 (single optional param, full schema coverage, no nested objects), the description is largely complete. The main gap is the return value: with no output schema in place, the description does not tell the agent what the scan yields (e.g., matched files, line numbers, severity), so an agent cannot predict how to interpret results. This is a minor gap for an otherwise simple 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 description coverage is 100% and the single parameter targetDir is already documented as 'Target directory to scan (defaults to cwd)'. The description adds no parameter-specific detail beyond the schema, so it does not exceed the baseline for a fully-covered one-parameter tool.

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 uses a specific verb ('Scans'), names the resource ('repository text files'), and enumerates the precise targets ('accidentally hardcoded API keys, JWTs, and private tokens'). It clearly distinguishes itself from the sibling security_auto_sanitize_secrets by framing this as detection ('scans') versus remediation ('sanitize'), so an agent can tell them apart without opening schemas.

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 intended context (pre-commit secret detection) is implied by the purpose, but the description offers no explicit when-to-use or when-not-to-use guidance, no prerequisites (e.g., git repo, network access), and does not route the agent to the complementary sibling security_auto_sanitize_secrets once findings are discovered. The use case is inferable but never stated.

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