ai_code_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. It usefully discloses auto-skipped directories and binary files, which an agent could not infer otherwise, but says nothing about read-only safety, traversal limits, or whether it follows symlinks. The maxFiles cap is only in the schema, not the prose.

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?

Two tight sentences with the core action and the notable skip behavior front-loaded. No filler or restated name.

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 scanner with no annotations and no output schema, an agent still does not know what a result looks like (findings, severities, file/line references) or how large directories behave. The behavioral basics are covered, but return-value expectations and limits are left implicit.

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 with examples and defaults. The description adds nothing about the interplay between exclude/include or the default 5000-file cap, so baseline 3 applies.

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?

States a specific verb ('Recursively scan') and resource ('a directory') plus the target domain ('insecure AI/LLM integration patterns'). However, it does not distinguish this tool from the many sibling scan_directory tools (a2a_auditor, elicitation_auditor, tool_poisoning_scanner, etc.) that appear to operate identically on different pattern sets.

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?

Usage is implied by the name and by the 'directory' scope, which implies scan_file/scan_text siblings are for narrower inputs, but the description never states when to choose this over them. No exclusions, prerequisites, or alternative-selection guidance is given.

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