scan_local

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

Annotations already declare readOnlyHint=true and openWorldHint=false. The description adds critical behavioral details beyond annotations: 'Never modifies scanned files', 'No authentication required', and 'Returns redacted findings — raw secret values are never included'. No contradictions.

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?

Three sentences covering purpose, locality, safety, and output redaction. Every sentence adds value. No redundant or unnecessary text. Front-loaded with the primary action.

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?

The description effectively covers core behavior and safety. With an output schema available, return values are partially explained (redacted findings). It omits details about optional parameters like regex_file or show_matched_secret_on_logs, but these are in the schema. Adequate for a moderately complex 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%, so baseline is 3. The description does not elaborate on individual parameters beyond what the schema provides. However, it summarizes the overall behavior (scan path, report format, etc.) without adding new semantic meaning for parameters.

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 local filesystem for leaked secrets, listing specific secret types. It distinguishes itself from sibling tools that scan remote platforms (e.g., scan_github) by emphasizing 'Fully local — no network calls'. The action and resource are both specific and unique.

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 provides clear context: when to use (local filesystem scanning), what it doesn't do (no network calls, no data sent externally), and prerequisites (no authentication required). It lacks an explicit comparison to siblings, but the 'local' distinction is evident from sibling names.

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