web_search

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

No annotations, so description must carry transparency. It discloses provider resolution behavior, that results are ranked, synthesized answers are optional per provider, and setup fallback. Missing rate limits/error details, but covers key operation traits.

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?

Three focused sentences: purpose, provider context, fallback guidance. No filler.

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?

Tool has 4 params and no output schema; description explains what it returns (ranked results, maybe summary) and how provider is selected. Slight gap on exact return structure, but acceptable.

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 already covers all 4 params with descriptions (100% coverage), baseline 3. Description adds context about provider options (e.g., gemini CLI no API key) and auto-resolving, enriching the provider param beyond the enum.

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?

States 'Search the web for a query and return ranked results', a specific verb-resource combination. Distinguishes from siblings like search_tools by explicitly targeting web content. Also notes synthesized answer when provider offers.

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?

Gives clear context: uses configured provider, and if none set up, explains how to enable. Doesn't explicitly contrast with alternative tools like search_tools, but the web-search scope is unambiguous.

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