agent_graph_auditor__scan_directory

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

With no annotations at all, the description carries the full behavioral burden, and it does disclose a genuinely important limitation: each file is analyzed independently and variable references do not resolve across files, so cross-file Crew/GroupChat assembly is not connected. That is exactly the kind of caveat an agent needs to interpret results correctly. It still omits read-only-ness, performance/scale behavior, and what the report looks like, so it falls short of a 5.

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 sentences, no filler. The core action is front-loaded and the second sentence is a non-obvious caveat that earns its place by preventing misreading of results.

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, no-annotation, no-output-schema scanning tool, the description tells the agent what is scanned, what is reported, and the key analytical limitation. It does not describe the shape of the report or pagination/truncation behavior, which is the main remaining gap.

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%, with path, exclude, include and maxFiles all documented in the schema, so the baseline is 3. The description adds no extra meaning about path syntax, exclude/include matching semantics, or the default file cap beyond what the schema already says.

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), resource (a directory of Python files) and output (excessive-agency paths found in each). It is clearly the batch counterpart to the sibling scan_file/scan_text tools, but it never names them, so the differentiation is implied by the word 'directory' 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?

The word 'directory' and 'Recursively' imply the right usage context versus a single-file scan, but there is no explicit when-to-use statement, no mention of when to prefer scan_file or scan_text, and no prerequisites. Usage is inferable, not stated.

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