Skip to main content
Glama
FamilySearch MCP Server

FamilySearch MCP Server

by G4rutti

get-image

Returns record images or zoomed crops inline for reading handwriting, with optional high-contrast enhancement for faded ink.

Instructions

Return a record image (or a zoomed-in part of it) inline, for reading handwriting. Coordinates are 0-1 fractions of the full scan: x/y is the top-left corner, width/height the size (e.g. x 0.5, width 0.5 is the right-hand page). The output is capped at maxWidth pixels and never upscaled, so crop small to read small writing. enhance: true turns faded ink into high-contrast grayscale. Faster and lighter than download-document.

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"
  }
}

Input Schema

NameRequiredDescriptionDefault
xNoLeft edge, 0-1 (default 0)
yNoTop edge, 0-1 (default 0)
widthNoCrop width, 0-1 (default: to the right edge)
heightNoCrop height, 0-1 (default: to the bottom edge)
enhanceNoGrayscale + auto-contrast for faded ink (default false)
imageIdNoImage ID (3:1:...) or ARK URL
maxWidthNoOutput width cap in pixels (default 1600)
waypointNoWaypoint (see browse-waypoints), used with imageNumber instead of imageId
imageNumberNo1-based image number inside the waypoint

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv2.2.0

TDQS

A4.4/5.0
Behavior4/5

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

With no annotations, the description carries the full burden and does a solid job: inline delivery, output capped at maxWidth, never upscaled, and enhance converting faded ink to high-contrast grayscale. It omits failure behavior and does not state that one of imageId or waypoint+imageNumber must actually be supplied.

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?

Four tight sentences: purpose first, then coordinate semantics, then output/cropping constraints, then the enhance flag. Every sentence contributes actionable information and nothing is repeated from the schema.

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 annotations and no output schema, this covers most of what an agent needs: what comes back, sizing limits, and how to crop for legibility. The main gap is that zero parameters are strictly required, yet the description never explains that imageId or the waypoint+imageNumber pair must be provided.

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 baseline is 3, but the description genuinely adds meaning: coordinates as 0-1 fractions of the full scan with a concrete worked example (x 0.5, width 0.5 = right-hand page), the fact that output is capped and never upscaled, and what enhance does to the pixels. It does not clarify the imageId vs. waypoint/imageNumber relationship.

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?

Opens with a specific verb and resource: 'Return a record image (or a zoomed-in part of it) inline, for reading handwriting.' It also explicitly positions itself against the sibling download-document, so an agent can choose between them without inspecting schemas.

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

Usage Guidelines4/5

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

The use case is stated ('for reading handwriting') and the trade-off against download-document is given ('faster and lighter'). It also supplies a tactical heuristic ('crop small to read small writing'). It stops short of an explicit when-not or a definitive rule for choosing between the two tools.

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