lucky_list_local_pathsList filesystem roots or files under a specified path to view local directories as Lucky sees them. Resolve visibility issues by checking which paths are accessible.
List filesystem roots, or files under a path, as Lucky sees them.
| Name | Required | Description | Default |
|---|---|---|---|
| path | No |
Changes observed during successful MCP inspections.
v0.1.3Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare the operation read-only, idempotent, and non-destructive, so the safety profile is known. The description adds the contextual detail that results reflect Lucky's view of the filesystem, which is useful. It does not disclose behavior for invalid paths, hidden files, recursion, or path format, but for a simple list operation the annotations carry much of the burden.
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?
A single 12-word sentence conveys the full behavior without filler. The conditional behavior (roots vs files under path) is front-loaded and immediately usable. No sentence is wasted.
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 read-only tool with one optional parameter, the description covers the essential behavior: roots without a path and files under a path. Annotations supply the safety profile, and the output type is self-evidently a listing. The main gaps are path format and recursion semantics, which are minor for a simple browse operation.
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?
The schema has one optional 'path' string with 0% description coverage, so the description must compensate. It effectively does: 'roots, or files under a path' tells the agent that omitting path lists roots and providing it lists entries beneath it. It does not specify absolute vs relative path syntax or whether recursion is included, but the core semantic is communicated.
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 uses a specific verb ('List') and a precise scope: filesystem roots when no path is given, or files under a given path. The qualifier 'as Lucky sees them' clarifies that this is Lucky's view of the filesystem, distinguishing it from generic host filesystem tools. No sibling tool covers this same resource, so it is easy to identify.
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 description implies the main use case: exploring the filesystem from Lucky's perspective. It distinguishes root-level listing from path-scoped listing by the optional path argument, which gives conditional guidance. However, it does not explicitly name alternatives or state when not to use this tool; with 40+ siblings, a pointer to related storage or file tools would have been helpful.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.