listDir

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

With no annotations, description carries full burden. It discloses non-recursion, blocked sensitive system paths, and output format (formatted table with columns). No contradiction with annotations (none present). Missing discussion of error behavior or performance, but adequate for a list tool.

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?

Four sentences with clear front-loading: purpose + output, usage, recursion guidance, security. No redundant information. Each sentence serves a distinct purpose.

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?

Given no annotations or output schema, the description covers essential aspects: what it does, how to use path, what it returns, limitations (non-recursion, blocked paths). Minor omission: doesn't specify behavior for invalid paths, but overall complete.

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 coverage is 100%, so baseline is 3. The description reinforces path usage (absolute/relative, empty/null byte restrictions) but does not add new semantics beyond the schema explanation. The examples in schema are sufficient.

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?

Clearly states 'List the contents of a directory with metadata for each entry', specifying verb and resource. The columns (Type, Size, Modified, Name) make the output explicit. Distinguishes from sibling tools like readFile and exec by focusing on directory listing.

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?

Describes when to use: 'explore the filesystem, discover files, or verify directory structure'. Explicitly warns that it does not recurse and instructs to call again on child directories. No missing exclusions or comparisons to siblings, but context is clear.

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