Skip to main content
Glama
FamilySearch MCP Server

FamilySearch MCP Server

by G4rutti

search-full-text

Search FamilySearch AI-generated full-text transcripts of unindexed document images by name, place, year, keywords, or collection to locate relevant historical records.

Instructions

Search FamilySearch AI-generated full-text transcripts of unindexed document images

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "search-full-text"
  }
}

Input Schema

NameRequiredDescriptionDefault
limitNoMaximum results (default: 5, max: 20)
placeNoPlace mentioned in or associated with the document
offsetNoResult offset for pagination (default: 0)
yearToNoLatest year
fullNameNoPerson name to find in the document
keywordsNoWords or phrases anywhere in the OCR transcript; supports FamilySearch search syntax
yearFromNoEarliest year
matchModeNoHow multi-word keywords and names are matched: any (OR, default), all (AND), or exact phrase
collectionIdNoRestrict the search to a Full-Text collection ID
imageGroupNumberNoFamilySearch DGS/image group number
includeFullTranscriptNoReturn complete OCR text instead of an excerpt; use with a low limit

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv2.2.0

TDQS

B3.4/5.0
Behavior3/5

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

With no annotations, the description carries the full burden, and it does disclose meaningful source characteristics: the transcripts are AI-generated OCR of unindexed images, implying possible transcription error and a different index than metadata records. However, it says nothing about authentication requirements, result volume, rate limits, or the practical difference between excerpt and full-transcript responses.

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?

A single front-loaded sentence that identifies the resource, its source, and its distinguishing scope with zero filler. Nothing could be removed without losing information.

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

Completeness2/5

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

An 11-parameter, zero-required search tool with no annotations and no output schema gets only one sentence. Key things an agent needs — when to prefer this over indexed-record search, how results are shaped, and how matchMode/limit interact with includeFullTranscript — are left entirely to the schema.

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%, so every one of the 11 parameters is already documented, including matchMode semantics and the includeFullTranscript caveat. The description adds no parameter-specific guidance beyond the schema, which is the expected baseline when the schema does the heavy lifting.

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 ('Search') and a precise resource ('FamilySearch AI-generated full-text transcripts of unindexed document images'), which distinguishes it in substance from siblings like search-records and search-catalog. It stops short of explicitly naming those alternatives, but the 'unindexed document images' scope makes the boundary inferable.

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?

Usage is only implied: 'unindexed' suggests this is the fallback when indexed record searches return nothing, but the description never states when to choose it over search-records or search-persons, nor any prerequisites. An agent must infer the routing decision from the word 'unindexed' alone.

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