search_code

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

With no annotations provided, the description carries the full burden of behavioral disclosure. It explains that sort and order are omitted due to GitHub closing sortable code search and that results are ranked by relevance. This adds useful behavioral context beyond a simple 'search' description, though it does not cover rate limits or return types.

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 plus a docs link, with the purpose front-loaded in the first sentence. Every sentence adds value: purpose, query syntax example, behavioral note, and reference documentation. No fluff or repetition of schema information.

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?

This is a search tool with no output schema, so the description needs to convey how to query and what to expect. It covers qualifiers, ranking, and the rationale for omitted sort/order, and provides a direct docs link for deeper reference. While it doesn't detail the return structure, that is reasonably implied for a code search tool and supplemented by the docs link.

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 description coverage is only 33% (only q is described), so the description must compensate. It adds a concrete example for the q parameter ('addClass repo:jquery/jquery in:file language:js') which is more illustrative than the schema's list of qualifiers. However, page and per_page parameters are not described in the tool description, leaving them solely to schema defaults and types.

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 'Search code across GitHub' with a specific verb and resource, distinguishing it from sibling tools like search_repos, search_commits, etc. It also provides example qualifiers that reinforce its code-specific scope. No ambiguity remains about what the tool does.

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 does not explicitly state when to use this tool versus alternatives or when not to use it. While it implies usage for code search, it fails to mention that other search tools (search_repos, search_issues) exist for different resources. No exclusions or alternative tool references are provided.

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