Firecrawl MCP Server

Firecrawl read research paper

firecrawl_research_read_paper

Read-only

Extract in-body passages from a specified paper that answer a research question. Returns matching text or a notice when full text is unavailable.

Instructions

Retrieve in-body passages from one paper that are relevant to a specific question. Full text is available only for indexed papers; k controls the number of passages.

Returns matching passages or a notice when full text is unavailable.

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": {
      "paperId": "<paperId>",
      "question": "<question>"
    },
    "name": "firecrawl_research_read_paper"
  }
}

Input Schema

Name	Required	Description
`k`	No	Number of passages to return (default 4).
`paperId`	Yes	Canonical paperId or primaryId such as `arxiv:1706.03762`, `pmcid:PMC12530322`, `pmid:40953549`, or `doi:10.1016/j.neunet.2025.108095`.
`question`	Yes

Output Schema

Name	Required	Description	Default
`passages`	Yes	In-body passages relevant to the question; empty when no full text is indexed.
`agent_hints`	No	Optional response guidance from the Firecrawl API.

Schema Changelog

Changes observed during successful MCP inspections.

First observedv3.28.2Nov 4, 2026

TDQS

A3.8/5.0

Behavior4/5

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

Annotations already declare readOnlyHint, openWorldHint and destructiveHint=false, so the safety profile is covered. The description adds genuine behavioral context beyond that: the indexed-papers prerequisite and the explicit 'notice when full text is unavailable' failure mode, which is exactly the kind of thing annotations cannot convey. It does not discuss rate limits or cost, keeping it just short of a 5.

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?

Three short sentences, purpose front-loaded, no filler adjectives or marketing language. The closing sentence about return values is somewhat redundant given an output schema exists, which keeps it from a 5.

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

Completeness5/5

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

An output schema exists, so the description need not enumerate return fields, and it correctly spends its budget on purpose, the indexed-paper prerequisite and the unavailability case. For a 3-parameter read-only retrieval tool, nothing an agent needs in order to call it correctly is missing.

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 67%, so most parameters are already documented, and the description's note that '`k` controls the number of passages' largely restates the schema's own 'Number of passages to return (default 4)'. The one real addition is framing 'question' as the semantic relevance driver for passage selection, since the schema leaves that parameter undescribed. Baseline 3 fits.

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 gives a specific verb and resource: 'Retrieve in-body passages from one paper that are relevant to a specific question.' That is far more precise than a generic 'read paper' and implies retrieval restricted to one paper and to question-relevant passages. It does not explicitly name the sibling it differs from (e.g. firecrawl_research_inspect_paper), so the differentiation is left implicit.

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

Usage Guidelines3/5

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

The description supplies one real usage condition, 'Full text is available only for indexed papers', which tells the agent when this call will fail. However, it never states when to choose this over firecrawl_research_inspect_paper or firecrawl_research_search_papers, which is the key routing decision in this sibling cluster.

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