Skip to main content
Glama
Scormave

Gramps Web MCP

by Scormave
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Hybrid

Get Relations

get_relations
Read-only

Explain how person 2 is related to person 1, showing the closest relationship and all common ancestors. Searches up to 15 generations of blood relatives and spouses.

Instructions

Explain how two people are related, read as 'person 2 is the X of person 1' (e.g. 'third cousin twice removed', 'husband'): the closest relationship with generations to the common ancestor, then every relationship found with its common ancestors by name. Searches blood relatives up to 15 generations plus spouses; unrelated people get a clear message. Find both people first with search. To list a whole line of ancestors or descendants use get_person_tree.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
handle1YesPerson 1, the one the relationship is told from. Handle or Gramps ID (e.g. I0001), resolved automatically; find it with search or list_objects.
handle2YesPerson 2, the one whose relationship to person 1 is named. Handle or Gramps ID (e.g. I0001), resolved automatically; find it with search or list_objects.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changedv2.3.0
    • changedInput schema / properties / handle1 / description
      Previous value: -"First person handle. Handle or Gramps ID (e.g. I0001). Handles are opaque strings from the API. Gramps IDs (like I0001, F0023) are auto-resolved to handles. Find handles with search() or list_objects()."New value: +"Person 1, the one the relationship is told from. Handle or Gramps ID (e.g. I0001), resolved automatically; find it with search or list_objects."
    • changedInput schema / properties / handle2 / description
      Previous value: -"Second person handle. Handle or Gramps ID (e.g. I0001). Handles are opaque strings from the API. Gramps IDs (like I0001, F0023) are auto-resolved to handles. Find handles with search() or list_objects()."New value: +"Person 2, the one whose relationship to person 1 is named. Handle or Gramps ID (e.g. I0001), resolved automatically; find it with search or list_objects."
  2. First observedv2.2.0

TDQS

A4.6/5.0
Behavior4/5

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

Annotations already declare this a safe read (readOnlyHint=true, destructiveHint=false), so the bar is lower; the description still adds real behavioral scope: blood relatives up to 15 generations plus spouses, and an explicit edge-case behavior for unrelated people (a clear message rather than silence). It does not cover performance or pagination, which keeps it short of a 5.

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?

Front-loaded with the core semantics and direction convention, then the return shape, then scope limits and the sibling routing. Every sentence carries information, though the single dense paragraph packs several distinct ideas without visual separation.

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?

No output schema exists, and the description compensates by describing the result content: the closest relationship with generations to the common ancestor, followed by every relationship found with its common ancestors by name. Combined with the scope limits and prerequisite, an agent has everything needed to call it correctly.

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 both parameters already document handle/Gramps ID resolution, so the baseline is 3. The description goes beyond that by defining the semantic asymmetry of the two handles — the relationship is told from person 1 and named for person 2 — which the schema alone does not convey as clearly.

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 (explain how two people are related) and immediately pins down the reading convention: 'person 2 is the X of person 1', with concrete examples. It also names what it is not, steering the agent away from get_person_tree for line-of-descent queries.

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?

Gives explicit prerequisites ('Find both people first with search') and names the alternative tool with the condition that selects it ('To list a whole line of ancestors or descendants use get_person_tree'). Nothing about when to pick this tool is left to inference.

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

Deploy Server

Other Tools