search_code

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

No annotations are provided, so the description carries the full burden. It discloses that the tool returns a lightweight index (not full source) and implies read-only behavior. It does not mention auth, rate limits, or cost, but for a search tool this is reasonable. The behavioral traits are well explained.

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, front-loaded with purpose, then condensed usage workflow. Every sentence is purposeful: first sentence defines what it does, second provides an efficient exploration strategy. No wasted words.

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?

Despite no output schema, the description explains return format (file paths, line numbers, short previews) and integrates with sibling tools. It addresses the broader context of token-efficient code exploration, making it complete for its role.

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 100%, so the baseline is 3. The description does not repeat schema details but adds context on how to use extensions to exclude content files, which adds value beyond the schema. It implies the query parameter is for natural language, consistent with 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 it's a semantic search in code using OpenAI embeddings, returns file paths, line numbers, and short previews, and explicitly says what it does NOT return (full source). It distinguishes from sibling tools like search_docs and get_file_outline.

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 frames search_code as 'STEP 1 of token-efficient exploration' and provides a concrete workflow: call search_code, then get_file_outline, get_file_folded, get_symbol. It explicitly advises against reading whole files and points to better tools, giving clear when-to-use and when-not-to-use guidance.

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