Skip to main content
Glama

Firecrawl by Nova (CIVAI)

firecrawl_research_lookup_protein

Look up one protein in UniProtKB/Swiss-Prot, the reviewed section of UniProt, and return what its curators state: subcellular location, function, and GO cellular-component terms. Use this when the question is where a named protein is located in the cell, what it does, or which compartment terms it has, and you have a UniProt accession (P05771), an entry name (KPCB_HUMAN), a gene symbol (PRKCB), or the exact protein name. One protein per call; organism defaults to human.

Each location and function statement carries an evidence label and, where UniProt cites one, a pmid: paper ID. Among these statements, only those whose label starts with "Experimental" are measurements. Every other label, such as "Inferred from a related protein", "Curator inference", "Predicted from sequence", or "No evidence tag", is not, so report the label with the statement. The GO cellular-component terms carry no such label. Every GO term listed has experimental evidence, shown by its GO code (IDA and the like) and the group that assigned it. When a location statement and a GO term name the same compartment with different evidence, say which one the compartment rests on, for example "curated location has no evidence tag; GO term mitochondrion is experimental, IDA, HPA". Open a cited paper with firecrawl_research_inspect_paper or firecrawl_research_read_paper.

Not for free-text questions, topics, diseases, or lists of proteins (use firecrawl_research_search_papers), and not for structures, compounds, interactions, or unreviewed entries. If a symbol names several proteins, the result lists candidates; call again with one accession.

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": {
      "protein": "<protein>"
    },
    "name": "firecrawl_research_lookup_protein"
  }
}

Input Schema

NameRequiredDescriptionDefault
proteinYesOne protein identifier: a UniProt accession (`P05771`; an isoform ID such as `P05771-2` resolves to its entry), an entry name (`KPCB_HUMAN`), a gene symbol (`PRKCB`), or the exact protein name (`Protein kinase C beta type`). Not a question or a sentence.
organismNoOrganism that scopes a gene symbol or protein name: an NCBI taxon ID (`10090`), a scientific name (`Mus musculus`), or a UniProt common name (`Mouse`). Defaults to human (`9606`). Accessions and entry names ignore it.
objectiveNoThe user's underlying goal in one sentence, not a restatement of this call's arguments. Reuse it across related calls. Firecrawl uses it to learn what agents need and improve its results. No personal data, secrets or the user's exact words.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • addedInput schema / properties / objective
      Added value: +{
      +  "description": "The user's underlying goal in one sentence, not a restatement of this call's arguments. Reuse it across related calls. Firecrawl uses it to learn what agents need and improve its results. No personal data, secrets or the user's exact words.",
      +  "maxLength": 5000,
      +  "minLength": 1,
      +  "type": "string"
      +}
  2. Added

TDQS

A4.6/5.0
Behavior4/5

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

With no annotations, the description carries the full behavioral burden and does so unusually well: it explains that only labels starting with 'Experimental' are measurements, that all other labels must be reported alongside the statement, that GO terms carry GO codes and assigning groups, and that PMIDs can be opened with inspect_paper/read_paper. It does not mention cost/credit implications or result-size limits, which is the only material gap for a tool with zero annotation coverage.

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?

Purpose and trigger conditions are front-loaded in the first two sentences, and the negative scoping sits at the end where it belongs. It runs four dense paragraphs and the evidence-label passage is lengthy, but nearly every sentence carries decision-relevant information rather than filler.

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?

There is no output schema, yet the description fully compensates by describing what is returned, how evidence labels and GO codes should be interpreted and reported, and the cross-tool follow-up for cited papers. An agent can call this and correctly interpret the response without additional context.

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

Parameters4/5

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

Schema coverage is 100% and the schema already documents all three parameters in detail, so the baseline would be 3; the description still adds the operational rules the schema does not spell out — 'one protein per call' and '`organism` defaults to human' — plus the candidate-list fallback. The rest (identifier forms) largely restates the schema's own parameter text.

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

Purpose5/5

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

The description opens with a specific verb and resource — 'Look up one protein in UniProtKB/Swiss-Prot, the reviewed section of UniProt' — and names the exact payload returned (subcellular location, function, GO cellular-component terms). The 'reviewed section' qualifier and the one-protein-per-call scope make it unmistakable against siblings like search_papers.

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

Usage Guidelines5/5

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

It states the triggering question shapes (where a named protein is located, what it does, which compartment terms it has), the acceptable identifier forms, and explicit exclusions: 'Not for free-text questions, topics, diseases, or lists of proteins (use firecrawl_research_search_papers), and not for structures, compounds, interactions, or unreviewed entries.' It also handles the ambiguous-symbol case with a concrete next step ('the result lists candidates; call again with one accession').

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.

Resources