Spend Brake

Exa search (capped)

exa_search

Search the web through Exa while enforcing a hard spend cap; each call reports its cost and remaining budget so agents can stay within limits.

Instructions

Search the web with Exa. Each call is charged against a hard spend cap; the result shows its cost and the budget left.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "query": "<query>"
    },
    "name": "exa_search"
  }
}

Input Schema

Name	Required	Description
`text`	No	Include each page's text (costs extra per result)
`type`	No	auto (default); lite and instant are cheaper, deep costs more
`query`	Yes	What to search for
`numResults`	No	Default 5; each result above 10 costs extra
`excludeDomains`	No	Never these domains
`includeDomains`	No	Only these domains
`startPublishedDate`	No	ISO date, e.g. 2026-01-01

Schema Changelog

Changes observed during successful MCP inspections.

First observedv0.1.0Nov 9, 2026

TDQS

A3.6/5.0

Behavior4/5

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

Annotations declare readOnlyHint=false, openWorldHint=true, idempotentHint=false and destructiveHint=false, so the safety profile is already covered. The description adds genuinely non-redundant behavior: every call is billed against a hard cap and the response surfaces the cost plus remaining budget, which explains why a 'search' is not marked read-only. It does not say what happens when the cap is exhausted.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Two short sentences with zero filler, and the core action is front-loaded before the cost caveat. Every clause carries information an agent needs before calling.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a 7-parameter, fully documented, side-effecting search tool with no output schema, the description covers the action and the billing/return behavior that the annotations imply. The remaining gap is sibling routing against tavily_search, which matters given two search tools are exposed.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, including per-parameter cost notes on 'text', 'type' and 'numResults', so the schema carries the semantic load. The description adds no parameter meaning beyond that, making the baseline 3 appropriate.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description states a specific verb and resource ('Search the web') and names the provider ('with Exa'), which lets an agent distinguish it from the sibling tavily_search without opening either schema. It stops short of stating any scope or differentiating characteristics beyond the vendor name.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines2/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

There is no when-to-use guidance and no mention of the sibling tavily_search, which is the most likely alternative for the same job. The spend-cap sentence is cost context, not a condition for selecting this tool over another, so selection is left entirely to inference.

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

Deploy Server