web_search

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

Annotations only give generic hints (readOnlyHint=false, openWorldHint=true), so the description carries real weight and does: it discloses the monetary side effect (0.01 USDC per call, auto-paid over x402 on Base), the precondition (AGENT_PRIVATE_KEY configured, price within MAX_USDC_PER_CALL), and that no model is used. This explains why readOnlyHint is false for an otherwise read-like operation.

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?

Front-loaded with purpose, then exclusions and alternative, then cost preconditions — a sensible order with no filler. The cost sentence is dense with configuration conditions, and the leading 'Web search:' label partly restates the title, but every sentence still carries useful information.

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 no output schema, the description correctly spends space enumerating return fields, and it covers cost, preconditions, scope limits, and the excluded follow-up operation. For a six-parameter, externally-billed search tool, an agent has everything needed to decide and invoke 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 already 83%, so the baseline is 3; the description adds a little by tying the 10-result cap to 'up to 10 ranked results' and linking 'highlights/extra snippet text' to include_text and 'published date' to date_from. It does not add format details for query, site, or date_from beyond the schema, so it stops short of full parameter guidance.

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 a specific verb and resource ('Runs a web search through a licensed search API (Exa or Brave)') plus the concrete return shape (up to 10 ranked results with title, URL, snippet, highlights, published date). It immediately disambiguates from the sibling 'page_contents' by declaring it does not fetch or summarize result pages.

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?

Explicitly names the audience/condition ('for agents that need current links'), the negative cases ('does not scrape search engines, does not fetch or summarize the result pages'), and the alternative to use instead ('use page-contents for that'). Provider selection guidance is also given: 'auto uses Exa when configured, else Brave.'

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