Web Search

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

Annotations already declare readOnlyHint, openWorldHint, idempotentHint, and destructiveHint, covering safety and side effects. The description adds behavioral details such as default timeout (2 minutes), ability to increase for complex queries, and control of verbosity via maxResponseLength. It does not describe rate limits or API costs, but given the annotations, this is sufficient.

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 well-structured with a clear purpose statement followed by bullet-point tips. It is front-loaded with the main function. One sentence could be removed (e.g., 'Results include source URLs for verification' is stated twice), but overall it is efficient.

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?

Given the tool's complexity (web search with synthesis) and the richness of annotations, the description covers key aspects: response includes URLs, timeout behavior, and length control. No output schema exists, but the description explains return format sufficiently. Missing details like error handling are not critical for basic use.

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 schema already documents all parameters. The description adds value by explaining when to adjust timeout and maxResponseLength, and how they affect behavior (e.g., complex queries may require multiple fetches). This goes beyond the schema's type/limit 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 clearly states 'Web search via Codex CLI' and 'Searches the web and synthesizes a comprehensive answer with source URLs', providing a specific verb and resource. However, it does not explicitly distinguish from sibling tools like 'query' or 'review', which may have overlapping purposes.

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 lists concrete use cases (current information, documentation lookups, API references, research) and provides actionable tips (ask specific questions, use maxResponseLength, adjust timeout). It lacks explicit when-not-to-use or alternative tool references, but the context is clear enough for an AI agent.

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