search_code

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

Annotations already declare readOnly, idempotent, and non-destructive hints, so the safety profile is covered. The description adds the behavioral detail of language prioritization but does not describe result ranking, filtering behavior, or the impact of tags/categories. This provides some added context beyond annotations but lacks richer behavioral disclosure.

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 a single, front-loaded sentence that distinguishes the tool's purpose and features without redundancy. Every word 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?

With an output schema and strong annotations, the description doesn't need to describe return values or safety. However, for a tool with 6 parameters and multiple sibling search tools, the description provides minimal usage context around filtering parameters and alternative tools, making it barely adequate for complex queries.

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 0%, so the description must explain parameters. It only gives semantic meaning to 'language' (prioritization), leaving 'tags', 'categories', 'canonical_urls', 'limit' undocumented. This is insufficient for a 6-parameter search tool with only one required field.

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 verb ('Search') and resource ('indexed code chunks'), and the word 'only' differentiates it from sibling search tools for docs, guides, and API. It also hints at language prioritization as a key feature.

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 phrase 'only indexed code chunks' provides clear context that this tool is for code-specific search, distinguishing it from search_docs and search_guides. However, it does not explicitly name alternative tools or state when not to use it, leaving some ambiguity for non-code search scenarios.

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