fs_search

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

With no annotations provided, the description carries the full burden of behavioral disclosure. It explicitly discloses a critical behavior: 'Any match that resolves outside FSGUARD_ROOT — e.g. via a symlink — is silently excluded rather than reported.' This is non-obvious and crucial for an agent to know. It also mentions recursion. However, it does not describe the return format or error handling, which would be helpful but is not essential for a simple 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?

Two sentences, no filler. The first sentence front-loads the primary purpose with a concrete example; the second adds a relevant caveat about sandboxing. Every word earns its place, and the structure is efficient and scannable.

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 the simplicity (2 params, no output schema), the description covers the essential context: recursion, glob matching, and the sandbox exclusion. It could explicitly state what the tool returns (e.g., a list of file paths) but that is inferable from 'Find files'. The non-obvious symlink behavior is disclosed, which is the most important missing context. Overall adequate for an agent to call it correctly.

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 must compensate. It explains the 'path' parameter as the base directory ('under path') and 'pattern' as a glob pattern with an example ('*.py'). This adds meaning to both parameters beyond the bare schema definitions. It could be more explicit about the path default and relative vs absolute paths, but the core semantics are clear.

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's function: 'Find files matching a glob pattern under path, recursively.' This specifies the verb (find), resource (files), and the pattern-matching behavior, distinguishing it from siblings like fs_list (which presumably lists without pattern filtering) and fs_read (which reads content). No ambiguity.

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 usage (searching for files by pattern) but does not explicitly state when to prefer it over alternatives like fs_list or when not to use it. It does not mention any exclusions or competing tools, leaving the choice to inference. A clear 'use this instead of fs_list when filtering by pattern' would elevate this.

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