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

Annotations already declare readOnlyHint=true (safe, non-destructive) and idempotentHint=true. The description adds value by specifying that the tool returns a synthesized answer, curated results with extracted content, and relevance scores, which are behaviors not captured by annotations. No contradiction with annotations.

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: the first introduces the core functionality and output, the second adds the intended use case and key features. Every sentence is meaningful, no redundancy or fluff. Concept is front-loaded.

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 has 7 parameters, a detailed output schema, and comprehensive annotations, the description covers the essential aspects: purpose, return content, typical use case, and filtering support. Minor missing context (e.g., credit cost for advanced depth) is already in schema descriptions.

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?

Input schema has 100% coverage with detailed descriptions for all 7 parameters (e.g., query, search_depth, include_answer). The tool description does not introduce new parameter information beyond what the schema already provides, so it meets the baseline expectation for high schema coverage.

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 specifies the tool's action: 'AI-optimized web search' that 'returns synthesized answer + curated results with extracted page content and relevance scores.' It distinguishes itself from siblings like `search.google.web` by emphasizing AI synthesis and RAG pipeline orientation.

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?

States it is 'Built for LLM/agent RAG pipelines,' providing clear context for when to use. However, it does not explicitly mention when not to use or compare with alternative search tools (e.g., `search.google.web` for raw results, `search.semantic.web` for semantic queries), which would improve guidance.

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