Skip to main content
Glama

search

Run parallel multi-engine web queries, fuse and rerank results with RRF and Jina, then return ranked JSON with provenance and engine health.

Instructions

Parallel multi-engine web search with RRF fusion and Jina reranking. Returns JSON with ranked results, engine provenance and engine health.

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": "search"
  }
}

Input Schema

NameRequiredDescriptionDefault
fastNoFan out one pool and return after the first sources.
queryYesSearch query.
top_nNo
answerNoAdd a cited answer section (needs local ollama).
expandNoRAG-Fusion variants (needs local ollama).
enginesNoComma-separated subset: exa,brave,serper,deepseek,firecrawl,anysearch,tavily,searxng.
no_jinaNoSkip reranking and keep the RRF order.
recencyNo
answer_deepseekNoUse the DeepSeek chat API for the answer section.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.2

TDQS

B3.4/5.0
Behavior3/5

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

With no annotations supplied, the description carries the full load and does disclose the return shape ('JSON with ranked results, engine provenance and engine health'), which hints at partial engine failures. However, it omits operational requirements the schema hints at — that answer/expand need a local ollama instance and answer_deepseek needs an API key — and says nothing about latency, rate limits, or external API dependencies.

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, zero filler, with the capability statement front-loaded and the return contract second. Nothing needs trimming.

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 9-parameter tool with no output schema and no annotations, the description covers the core capability and the return payload including engine health. The remaining gap is external dependency disclosure (ollama, DeepSeek, search API keys) that would determine whether several parameters will even work.

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 coverage is 78%, just below the high-coverage threshold, and the schema already documents most flags including no_jina's effect on RRF order. The description adds meaning only indirectly by naming RRF fusion and Jina reranking as the default pipeline, without explaining top_n semantics, recency behavior, or default engine selection.

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 ('Parallel multi-engine web search') plus the pipeline ('RRF fusion and Jina reranking'), which is far more informative than the bare name 'search'. It doesn't explicitly contrast with the sibling 'fetch', but the purpose is unambiguous.

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 guidance on when to use this versus 'fetch', nor when to enable fast, no_jina, answer, expand, or a restricted engines subset. The agent must infer all selection conditions from parameter names alone.

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

Deploy Server

Other Tools