Skip to main content
Glama

Tavily (Unofficial)

Tavily Search

tavily_search
Read-onlyIdempotent

AI/LLM-optimized web search built for RAG: returns a synthesized natural-language answer plus a ranked list of sourced results (title, url, content snippet, relevance score). Prefer this over scraping a generic search engine when you need grounded, citable web context. Example: search({ query: "latest SpaceX Starship test result" })

Example tool call

This call uses example arguments supplied in the tool’s input schema.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "query": "latest SpaceX Starship test result"
    },
    "name": "tavily_search"
  }
}

Input Schema

NameRequiredDescriptionDefault
queryYesThe search query / question to research.
topicNoSearch topic: "general" (default) or "news" for recent news coverage.
_apiKeyNoOptional, your own Tavily API key for higher limits; omit to use the shared Pipeworx key.
max_resultsNoMaximum number of results to return (default 5, max 20).
search_depthNoSearch depth: "basic" (fast, default) or "advanced" (deeper, more thorough).
include_answerNoWhether to include a synthesized AI answer string (default true).

Output Schema

NameRequiredDescriptionDefault
answerNoSynthesized answer; may be empty when nothing matched
resultsYes
response_timeNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • changedInput schema / properties / _apiKey / description
      Previous value: -"Optional — your own Tavily API key for higher limits; omit to use the shared Pipeworx key."New value: +"Optional, your own Tavily API key for higher limits; omit to use the shared Pipeworx key."
  2. Added

TDQS

A3.6/5.0
Behavior3/5

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

Annotations already declare readOnly, idempotent, openWorld and non-destructive, so the safety profile is covered. The description adds the return shape (synthesized answer + ranked sourced results), which is useful behavioral context. It says nothing about rate limits, authentication (the shared vs. own _apiKey tradeoff lives only in the schema), or result freshness, which are the remaining meaningful traits.

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

Conciseness4/5

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

Two front-loaded sentences deliver purpose, return shape and selection guidance with no filler. The trailing example is slightly redundant with the schema's own examples array, a small duplication in an otherwise tight definition.

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?

With an output schema, rich annotations and fully described parameters, the description only needs to orient and route the agent, and it largely does. The one notable omission is distinguishing this from tavily_news, an adjacent tool an agent could easily pick instead.

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%, with enums for topic and search_depth already documented, so the baseline is 3. The description's example queries illustrate realistic query phrasing but add no semantics about topic, search_depth, max_results or include_answer beyond what the schema states.

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 names a specific verb and resource ('AI/LLM-optimized web search built for RAG') and even characterizes the payload: a synthesized answer plus a ranked, sourced result list. That is a clear, agent-usable purpose statement. It stops short of differentiating from a close sibling like tavily_news, instead contrasting only with 'scraping a generic search engine'.

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

Usage Guidelines4/5

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

It gives an explicit selection cue — 'Prefer this over scraping a generic search engine when you need grounded, citable web context' — and backs it with a concrete example call. There is no when-not guidance and no routing to sibling alternatives such as tavily_news, so the alternative space is left implicit.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.