Skip to main content
Glama
FamilySearch MCP Server

FamilySearch MCP Server

by G4rutti

browse-waypoints

Browse a collection's image folders (place, town, register book) to see folder paths, sub-folders, and image counts, plus optional image IDs for use with get-image-index or get-image.

Instructions

Browse a collection's image folders (waypoints) the way the image viewer does: place > town > register book. Shows the folder path, its sub-folders, how many images it holds, and optionally the image IDs for a range. Start from a collection ID (e.g. 1582573), then pass a sub-folder URL; the wc= value of any image URL also works. Use the image IDs with get-image-index or get-image.

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": {
      "waypoint": "<waypoint>"
    },
    "name": "browse-waypoints"
  }
}

Input Schema

NameRequiredDescriptionDefault
waypointYesCollection ID (e.g. 1582573), a waypoint URL from a previous call, or the wc= value of an image URL (e.g. 9GRZ-FMD:113331301,113331302,113605501)
imageLimitNoHow many image IDs to list (default 0: only the count plus first and last image)
imageStartNoFirst image number to list (default 1)
collectionIdNoCollection ID, only needed with a bare wc= value

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv2.2.0

TDQS

A4.2/5.0
Behavior4/5

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

No annotations are supplied, so the description carries the full burden; 'Browse' plus the described return shape makes clear this is a read operation that navigates a hierarchy. It discloses the multi-format input behavior (collection ID -> waypoint URL -> wc= value) that an agent could otherwise miss. It does not cover failure modes, whether deep traversal is bounded, or rate/scope limits, which keeps it below a 5 for an unannotated tool.

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?

Three sentences, front-loaded with the resource and the mental model, then the workflow, then what to do with results. Dense but zero filler; the example IDs are load-bearing for format.

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?

With no output schema and no annotations, the description does the work of describing the return payload (path, sub-folders, count, optional IDs) and the input progression, which is enough for an agent to call it correctly. Minor gaps remain around error behavior and whether listing is bounded by folder size.

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 the schema already documents waypoint formats, imageLimit defaults, imageStart, and the collectionId pattern; the baseline is 3. The description adds the sequencing semantics ('optionally the image IDs for a range' spanning imageStart/imageLimit) and the progression from collection to sub-folder, which is modest value beyond the schema but not new parameter-level detail.

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?

States a specific verb and resource ('Browse a collection's image folders (waypoints)') and immediately grounds it with the concrete hierarchy 'place > town > register book'. It also enumerates what is returned (folder path, sub-folders, image count, optional image IDs), so an agent knows exactly what the call yields and can distinguish it from get-image/get-image-index, which it names as downstream consumers.

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?

Gives an explicit entry procedure: 'Start from a collection ID (e.g. 1582573), then pass a sub-folder URL', plus the shortcut that a wc= value works. It also tells the agent what to do with the output ('Use the image IDs with get-image-index or get-image'). It lacks an explicit when-not-to-use statement or a pointer away from the sibling list-film-images, which is the only real gap.

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