找路徑

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

With no annotations provided, the description carries the full burden. It discloses key behaviors: it skips .git and node_modules, and does not search file contents. This is valuable safety and scope information. It does not explicitly state read-only behavior, but 'search' implies no side effects, and there are no contradictory hints. Minor gaps like symlink handling or sort order exist, but coverage is good for a search 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?

The description is a single, compact sentence. It front-loads the core function ('glob path fuzzy search') and adds essential exclusions immediately. No filler or redundancy.

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 simple search tool with 3 parameters and no output schema, the description adequately covers the tool's scope and constraints. It does not mention return format (likely a list of paths) or edge cases, but those are implied and not critical for a basic glob search. The exclusions and content-search limitation add completeness beyond the bare minimum.

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 low (only glob has a description, root and limit have none). The description does not compensate by explaining root or limit. It only implicitly explains glob through the tool's purpose. For a low-coverage schema, the description should clarify all parameters, but it stays silent on root and limit, leaving agents to guess their meaning and defaults.

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 clearly states the tool performs a glob-based path search, with exclusions (skips .git/node_modules) and explicitly notes it does not search file content. This differentiates it from fs_grep (content search) and fs_ls (directory listing), making the purpose unambiguous.

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 when to use it (for path pattern matching) but does not explicitly compare with siblings or state when to avoid it. The note about not searching content hints at fs_grep as an alternative, but this is not made explicit. Lacks clear 'use this instead of X' guidance.

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