explore

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

With no annotations, the description carries full responsibility. It discloses that the tool is read-only ('never writes'), walks the filesystem, reads matched files, and returns a summary along with file:line matches capped at 15. It also notes the use of LLM summarization for deep depth. This is strong transparency, though it stops short of discussing performance or rate limits, which are less critical for a read-only search.

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 six sentences, each contributing distinct value: purpose, output type, usage trigger, alternatives, depth semantics, and return shape/safety. It is front-loaded with the core purpose and contains no filler or redundant restatements of the tool name or schema.

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?

There is no output schema, so the description's full return object specification (including fields like evidence with a cap of 15) is essential and well-covered. It includes safety behavior, usage scenarios, and parameter semantics. For a search tool with nested options, this description is thorough and leaves no major gaps.

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 description adds meaning to the 'depth' parameter (shallow = fast grep, deep = LLM context) and clarifies that 'question' is natural-language. It also references glob patterns within the tool's domain. However, it does not elaborate on 'backend', 'maxFiles', or 'scope' beyond the schema descriptions. With schema coverage at 50%, this partial compensation is adequate but not comprehensive.

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 as a natural-language codebase search with grep-style matching and optional LLM summarization. It distinguishes from siblings by explicitly naming analyze_file and batch_analyze as alternatives for different use cases, and provides concrete question examples ('where is X handled?').

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 gives explicit guidance on when to use this tool ('Use when you DON'T already know which file to look at') and when not, naming alternatives: use analyze_file for a known file and batch_analyze for a structured question across a known set of files. It also clarifies the depth parameter's shallow vs deep behavior.

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