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

With no annotations, the description carries the transparency burden, and it does so well: it discloses the exact response fields (position, title, url, snippet, direct answer, knowledge graph, related searches), the validity of zero results, and the commercial terms (per-call USDC cost, no account/API key). It does not mention rate limits or failure modes, but for a read-only search tool the core behavioral traits are covered. There is 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 front-loaded with the value proposition and price in the opening clause, followed by a compact enumeration of response contents, tuning parameters, and the zero-results note. Every sentence earns its place: output shape, behavioral note, cost, and auth requirements. There is no filler, repetition, or restating of the tool name.

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?

For a 4-parameter tool with no output schema, the description covers the key invocation facts: what the response contains, how to tune num/country/language, and the valid zero-results case. It also addresses practical concerns like cost and lack of authentication. Minor omissions such as rate limits and explicit error behavior are not critical for an agent to invoke this tool correctly.

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 four parameters with descriptions. The description adds a concise 'Tune with num (1-10 results), country and language (2-letter codes)' line that confirms these are optional tuning knobs, but it does not add semantic detail beyond what the schema provides. A baseline of 3 is appropriate since the schema does the heavy lifting.

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 uses a specific verb ('search') and resource ('web') and clearly states the output: compact JSON with organic results, direct answer, knowledge graph, and related searches. It makes clear this is a general web search, not a specialized news/image/places/scholar search, though it does not explicitly name sibling tools to rule out. The first sentence establishes the core purpose and audience ('for AI agents').

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 implies when to use this tool: when an agent needs a Google-quality general web search with structured JSON results, tunable by num, country, and language. However, it does not explicitly contrast with sibling tools such as news_search, web_images, or web_search_read, nor does it state when not to use it. 'Zero results is a valid, honest answer' provides some behavioral guidance, but no alternative tools are mentioned.

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