llm_fs_find

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

Disclosures routing to Haiku/Ollama and that Claude executes the commands, but lacks safety details (e.g., read-only? can it modify files?). With no annotations, description should cover behavioral traits more thoroughly, especially that it runs shell commands.

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?

Concise and well-structured. First sentence immediately states the purpose. Routing and execution details are provided concisely. Every sentence adds value without 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?

Given the simple parameters and presence of an output schema, the description fully covers what the tool does, how it works, and what it needs. No gaps for agent decision-making.

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?

Compensates for 0% schema coverage with rich examples and clear explanations. 'description' parameter is explained with realistic examples; 'root' parameter clarifies type, optionality, and default. Adds significant meaning beyond the bare schema.

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 it generates glob/grep commands to find files matching natural-language descriptions. Specific verb 'generate' and resource 'files' with a distinct approach (language-driven search) that differentiates it from sibling tools like llm_fs_analyze_context and llm_fs_edit_many.

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?

Implied usage: when you need to find files by description. But no explicit guidance on when to use this vs. alternative file tools (e.g., llm_fs_analyze_context for analyzing file context) or what to avoid. No when-not-to-use or alternative suggestions.

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