llm_fs_find

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

With no annotations, the description carries the burden for behavioral disclosure. It explains the two-step process (routing to Haiku/Ollama for pattern thinking, then Claude executing the commands). It does not contradict any annotations and gives sufficient insight into the tool's operation.

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 concise, with three sentences and a parameter list. It front-loads the purpose and provides necessary detail without unnecessary fluff.

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 that an output schema exists (handling return values), the description covers purpose, parameters, and behavioral asepcts adequately. It could optionally note that the tool returns commands, but completeness is high for a find tool.

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 input schema has 0% description coverage, so the description fully compensates by explaining the 'description' parameter with clear examples and the 'root' parameter with default behavior. This 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?

The description clearly states the tool generates glob/grep commands to find files based on natural language, using a specific verb ('Generate') and resource ('glob/grep commands to find files'). It distinguishes itself from sibling tools like llm_fs_analyze_context, llm_fs_edit_many, and llm_fs_rename.

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 provides context on when to use (finding files via natural language) and notes the routing to a cheaper model for pattern thinking. However, it does not explicitly state when not to use or compare with alternatives like llm_fs_analyze_context.

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