Spend Brake

Tavily search (capped)

tavily_search

Search the web through a budget-enforcing proxy that charges each call against a hard spend cap and returns the cost plus remaining budget.

Instructions

Search the web with Tavily. 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": "tavily_search"
  }
}

Input Schema

Name	Required	Description
`query`	Yes	What to search for
`topic`	No
`time_range`	No
`max_results`	No	Default 5
`search_depth`	No	basic (default) costs 1 credit; advanced costs 2
`include_answer`	No	Add a short generated answer
`exclude_domains`	No	Never these domains
`include_domains`	No	Only these domains

Schema Changelog

Changes observed during successful MCP inspections.

First observedv0.1.0Nov 9, 2026

TDQS

A3.5/5.0

Behavior4/5

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

The description adds real information beyond the annotations: each call is charged against a hard spend cap, and the response reports both its cost and the remaining budget. This explains the surprising readOnlyHint=false and idempotentHint=false annotations, which are otherwise confusing on a search tool, because the tool has a side effect on the budget. It does not say what happens when the cap is reached, for example whether the call fails or is refused.

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 sentences, front-loaded with the purpose, with no filler. The cost-and-budget clause is the single most important operational fact and is placed immediately after the purpose.

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

Completeness3/5

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

For an 8-parameter, open-world tool with no output schema, the description should at least say what the results contain, beyond the brief 'shows its cost and budget' note. It conveys the budget mechanism well but says nothing about result shape or relevance ranking, and it never mentions the brake_budget sibling that presumably controls the cap.

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 75% and the schema already documents most parameters (including cost per search_depth), so the baseline is 3. The description adds no information about parameters; it does not cover the undocumented topic and time_range enums, nor does it explain include_domains versus exclude_domains interaction.

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 with Tavily.' It is immediately clear what the tool does. It never names its siblings exa_search or brake_budget, though, so an agent must infer on its own which of the two search backends to call.

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?

It provides no when-to-use or when-not-to-use guidance; it never contrasts this tool with exa_search, the alternative web-search sibling, or with brake_budget. The only contextual cue is the cost warning, which is a behavioral constraint rather than a routing rule, so an agent gets no help choosing among the three tools.

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

Deploy Server