Skip to main content
Glama
FamilySearch MCP Server

FamilySearch MCP Server

by G4rutti

get-image-index

Reads indexed entries from consecutive record images, returning page and entry numbers, event dates, principals, parents and persona IDs for retrieving full records.

Instructions

Read the indexed records on one or more consecutive record images (the viewer's "Image Index" tab): entry and page numbers, event dates, the principals with their parents (and grandparents when indexed) and persona IDs for get-record. Walks forward with each image's next link, at the API pace (about 5 s per image), so keep count small; to find a name in a whole book, prefer search-records with filmNumber. Many images have no index at all: those come back empty and still need to be read with get-image.

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": "get-image-index"
  }
}

Input Schema

NameRequiredDescriptionDefault
countNoHow many consecutive images to read (default 1, max 10)
imageIdNoImage ID (3:1:...) or ARK URL of the first image
waypointNoWaypoint (see browse-waypoints), used with imageNumber instead of imageId
nameFilterNoOnly show records naming one of these comma-separated fragments (accents/case ignored), e.g. "symphr,sinfr,simphr"
imageNumberNo1-based image number inside the waypoint

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv2.2.0

TDQS

A4.8/5.0
Behavior5/5

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

No annotations exist, and the description carries the full burden: it discloses the sequential next-link walking behavior, the ~5 s per image API rate, the empty-result failure mode for unindexed images, and the fact that empty results still require a separate get-image call. That is unusually rich disclosure of cost and failure behavior for a read tool.

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?

The core purpose and the alternative routing are front-loaded, and every clause carries information. The single long sentence with parentheticals is dense and slightly hard to parse on first read, but there is no 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?

With no output schema and no annotations, the description supplies the return shape, the pagination/rate behavior, and the empty-result case. Nothing an agent needs in order to invoke this correctly or estimate its cost is missing.

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%, so the baseline is 3; the description adds real meaning to count by tying the small value to per-image pacing, and explains that persona IDs are usable with get-record. It does not mention nameFilter semantics, leaving that entirely to the schema.

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?

Names a specific verb and resource ('Read the indexed records on ... record images') and scopes it to the viewer's Image Index tab, enumerating exactly what comes back (entry/page numbers, event dates, principals plus parents/grandparents, persona IDs). An agent can distinguish this from get-image and search-records without opening a schema.

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?

Explicit routing: prefer search-records with filmNumber to find a name in a whole book, and fall back to get-image for images that have no index. It also states the pacing constraint (count small, ~5 s per image), which is effectively a when-not-to-use-large-counts rule.

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