search_code

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

With no annotations, the description must disclose behavior itself. It mentions an auth requirement (GITHUB_TOKEN) and describes the return format (matching files with highlighted fragments). However, it omits details like whether repo/owner are required, whether the search is read-only, pagination behavior, or any rate limits, so it only partially covers behavioral transparency.

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 two sentences, front-loaded with the primary purpose, and adds relevant details (highlighted fragments, auth token) without unnecessary verbiage. Every sentence earns its place.

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?

The tool has 6 parameters, no annotations, and no output schema, yet the description only covers the query string and return format. It does not clarify how to scope the search (owner/repo/path), the behavior of max_results, or the meaning of extension. This leaves significant gaps for an agent to use the tool 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?

The schema has 0% description coverage and 6 parameters, but the description only clarifies 'query string' and mentions 'repo' indirectly. It doesn't explain owner, path, extension, or max_results, leaving the agent to infer their meaning from the parameter names alone. This is insufficient compensation for the lack of schema descriptions.

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 states a specific action ('Search code in the repo') and identifies the primary resource ('code') and what it returns (matching files with highlighted fragments). It clearly distinguishes this from sibling tools like get_file_contents (which retrieves file contents) and list_symbols (which lists symbols).

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 (when you need to find code matching a query) but does not explicitly discuss alternatives or provide when-not-to-use guidance. It gives clear context for its core function but no exclusions or comparisons to sibling tools.

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