audit_directory_for_pii

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

Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false and openWorldHint=false, so the safety profile is covered. The description adds only that a summary report is returned; it does not disclose that scanning is local-only versus any quota/cost implications of profile selection, how large the scan may be, or what the report contains.

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 short sentences with the core purpose front-loaded and no filler or repetition. The closing 'Use this tool for Security Auditing' is the weakest sentence, adding a category label rather than actionable guidance, but it costs little.

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?

For a five-parameter tool with 30 specialized profiles and no output schema, the description is thin: it says a summary report is returned but does not characterize the report (findings list, severity, counts, remediation hints), so the agent cannot anticipate results. It is adequate to call the tool but not to interpret or follow up on its output.

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 all five parameters (directory_path, profile, sector alias, extensions, ignore_node_modules) are already documented in structured form. The description adds no meaning beyond the schema - notably it never mentions that 'sector' is an alias for 'profile' or that extension filters default to all text files.

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 names a specific verb and resource ('Scans a local directory') plus the target findings ('leaks of secrets, keys, and PII'), which clearly separates it from siblings like sanitize_file or redact_file that act on a single file. It stops short of explicitly contrasting itself with audit_context or the guard_* tools, so sibling differentiation is implicit rather than stated.

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?

'Use this tool for Security Auditing' is a blanket category label, not a when-to-use rule: it gives no preconditions, no when-not, and does not point at alternatives such as sanitize_file/redact_file for remediation or audit_context for contextual auditing. The agent must infer on its own when a directory scan is preferable to a file-level check.

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