mcp_config_auditor__scan_directory

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

With no annotations provided, the description carries the full burden, and it does disclose two useful traits: it only reads/audits (no server startup) and a directory scan additionally compares skill names. It omits other behavioral facts an agent would want — whether scanning is recursive, what happens on huge trees (it caps at maxFiles), and whether anything is mutated.

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, front-loaded with the core action and target file list, with zero filler. The 'compares skill names' clause is slightly abrupt but still earns its place as a behavioral note.

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 no-annotation, no-output-schema scan tool with a fully documented 3-param schema, the description covers what it targets and that it does not execute servers. It leaves gaps around recursion scope and what an audit returns, which matters for an agent deciding between this and the file/inventory variants.

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% and all three parameters (path, exclude, maxFiles) are documented in the schema. The description adds no parameter-level detail such as recursion behavior or how exclude/maxFiles interact with the scan, so this is the baseline case where the schema does the work.

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-plus-resource: find named config files (mcp.json, mcp_config.json, claude_desktop_config.json, SKILL.md) under a directory and audit each one, plus an extra behavior (comparing skill names). This clearly distinguishes it from sibling file/text scanners in the same family, but it does not explicitly contrast itself with mcp_config_auditor__scan_file or scan_inventory, so it stops short of full sibling routing.

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 (call it when you have a directory rather than a single file), and the negative clause 'Does not start any MCP server' rules out an expected-but-unwanted behavior. However, it never states when to prefer this over scan_file, scan_text, or scan_inventory for the same config content.

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