prompt_leak_scanner__scan_directory

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

With no annotations, the description carries the full behavioral burden, and it does add two useful traits: recursion and the class of content targeted (prompt logs / request-body fixtures). However, it says nothing about the read-only nature, the maxFiles truncation behavior implied by the schema, or what the scan returns, so it is only partially transparent.

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?

A single tight sentence with the verb and scope front-loaded and no filler. It is appropriately sized, though it could have spent one more clause on the directory-vs-file distinction at no real cost.

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 4-parameter scanner with full schema coverage but no output schema and no annotations, the description is minimally adequate. It never indicates what a scan produces (findings, counts, severities) or how truncation at maxFiles affects completeness, which an agent needs to interpret results.

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 four parameters (path, exclude, include, maxFiles) are already documented in the schema, including the 5000-file default. The description adds no syntax, ordering, or override details beyond that baseline.

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 gives a specific verb ('recursively scan'), a resource ('a directory of prompt logs or request-body fixtures'), and a detection target ('leaked credentials and PII'). It implicitly distinguishes itself from prompt_leak_scanner__scan_text and scan_file by operating on a directory, but it never names those siblings or states the distinction.

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?

There is no when-to-use guidance, no mention of when a directory scan is preferable to the text/file variants, and no prerequisites or exclusions. The agent must infer the choice purely from the tool name.

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