Deep research search via Exa (academic, boolean, multi-source synthesis). Fixed $0.015/call.
| Name | Required | Description | Default |
|---|---|---|---|
| query | Yes | Search query string | |
| country | No | ISO 3166-1 alpha-2 country code | |
| language | No | Language code (e.g. 'en', 'pt-PT') | |
| freshness | No | Recency filter for results | |
| max_results | No | Number of results (1-20, default 10) | |
| search_type | No | Type of search to perform |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the transparency burden. It discloses the fixed cost per call and the external provider (Exa), and hints at synthesis behavior. However, it does not state whether the tool is read-only, rate limits, or what the response format will be, which are significant behavioral gaps.
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 a single sentence that conveys purpose, provider, key capabilities, and cost. There is no unnecessary wording or redundancy, making it highly concise and 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?
Despite complete schema coverage, the description lacks crucial context for a tool with no output schema. It never states what the tool returns (e.g., a list of results vs. a synthesized narrative) or explains the operational difference from sibling search tools. This is a notable gap for a feature-rich 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?
The schema already documents all six parameters with descriptions, so baseline is 3. The description adds value by indicating that queries support boolean operators and that results involve multi-source synthesis, giving extra meaning to the query parameter and overall behavior beyond the schema.
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 identifies this as a deep research search tool via Exa, with explicit scope (academic, boolean, multi-source synthesis). The word 'deep' distinguishes it from the sibling tools, making its purpose specific and unambiguous.
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 usage for deep research (academic, multi-source synthesis) but does not explicitly state when to use this tool versus web_search_simple, web_search_medium, or web_search_cached. No exclusions or alternatives are mentioned, leaving the decision to inference from the name.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.
Each search tool has a distinct purpose: cached, deep, medium, and simple searches are clearly differentiated by query type and cost. The health tool is also clearly separate.
The four search tools follow a consistent web_search_<modifier> pattern, making their hierarchy obvious. The health tool breaks the pattern but is a standard auxiliary endpoint.
With 5 tools, the server is well-scoped for its purpose of routing search queries. Each tier earns its place without unnecessary duplication.
The search tiers cover a spectrum from cache-only to deep research, and the health check provides operational coverage. No obvious gaps in the search domain.