agent_graph_auditor__scan_directory

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

No annotations exist, so the description carries the burden — and it delivers a genuinely non-obvious behavioral trait: variable references do not resolve across files, so Crew/GroupChat members defined elsewhere will not be linked. That prevents misinterpretation of results. It omits safety profile (read-only) and any cost/limit context beyond the schema default.

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 zero filler; the scanning scope is front-loaded and the caveat follows immediately.

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?

No output schema, but the description indicates the return is per-file excessive-agency paths and warns about the main analysis limitation. It leaves the exact finding shape and behavior on very large trees (beyond maxFiles) unstated — a minor gap, not a blocking one.

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 path, exclude, include, and maxFiles are already fully documented. The description adds no syntax, format, or interaction detail for these parameters, 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 of Python files) plus the output (excessive-agency paths per file). It does not explicitly name scan_file/scan_text as the narrower alternatives, so sibling differentiation is only implied by the word 'directory'.

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?

Gives clear operating context: use this when you want whole-tree coverage, and expect per-file isolation rather than cross-file resolution. It stops short of explicit 'use X instead' routing or exclusions, so it is good context without full when/when-not guidance.

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