scan_directory

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

Annotations already cover safety (readOnly, idempotent, non-destructive, closed-world), yet the description adds substantial behavioral context beyond them: the exact skip list, the 5 MB file cap, best-effort .gitignore handling with its limitations, and truncation semantics when max_findings is hit.

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?

Front-loaded with the purpose, then structured Args/Returns sections. The skip list is long but each entry is informative; the only mild bloat is enumerating cache dirs that could be summarized.

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 exists, and the description compensates by describing the return shape (redacted findings report, root-relative forward-slash paths) and the truncation metadata. All three parameters and their edge cases are covered.

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 0%, so the description carries the burden and does so fully: path is documented as an absolute path, max_files and max_findings carry defaults and precise semantics ('0 = no limit'), plus the derived truncation fields emitted when capped.

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+resource+scope: 'Recursively scan a directory tree for exposed secrets.' An agent can tell it apart from scan_file/scan_text/scan_git_* by inference from 'directory tree', but no sibling is named explicitly, so it stops short of a 5.

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 resource ('scan a directory'), but there is no explicit when-to-use statement, no prerequisites, and no guidance on choosing this over scan_file or scan_text when a whole tree is not needed.

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