Real-time web search via Exa

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

The annotations already declare readOnlyHint: true, openWorldHint: true, idempotentHint: true, and destructiveHint: false, which cover safety and side-effect behavior. The description adds the cost detail and the specific result fields (title, URL, etc.), which are useful beyond the annotations. However, it does not elaborate on other behavioral aspects like rate limits, data freshness, or what happens if the query is empty, so the added value is moderate.

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, front-loading the core purpose and output fields, then appending cost. Every word adds value, with no fluff or redundancy. It is as concise as possible while being informative.

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 simplicity (2 params, no output schema, no nested objects, rich annotations), the description provides enough: purpose, output fields, cost, and implicit usage context. It lacks an explicit example or mention of return format limitations (e.g., pagination), but the annotations and schema already cover safety and parameter constraints, making this adequately complete for a search tool.

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%, meaning the schema already documents both parameters (q and numResults) with descriptions. The description adds the default count (5) and the range (1-10) for numResults, and the cost per call, but does not further clarify query syntax or formatting. Baseline 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 clearly states 'Real-time web search — ranked results with title, URL, published date, author, and relevance score for a query.', which specifies the verb (search), resource (web), and output fields. It distinguishes from siblings like get_protected_content (which likely retrieves a single protected page) and search_polymarket_markets (which is domain-specific), by indicating it searches the general web.

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 this tool is for real-time web searches where you need ranked results with structured metadata. It does not explicitly say when not to use it or name alternatives (e.g., for protected content, use get_protected_content), but the context signals and sibling list provide implicit guidance. The mention of cost ($0.003 per call) is an additional usage hint, though not a direct exclusion.

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