Skip to main content
Glama
ianderso

gramps-evidence-mcp

by ianderso
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Hybrid

verify_tree

Read-only

Run Gramps plausibility checks across a whole tree to flag impossible ages, marriages, sibling gaps, and bad dates that citations miss.

Instructions

Run Gramps' own genealogical plausibility checks over the whole tree.

This is a different audit from the citation ones. list_unsourced_facts asks whether a claim has evidence; this asks whether a claim is possible — a mother bearing a child at nine, a marriage lasting 120 years, a date that will not parse. A wrong date can be impeccably sourced, so these catch what a citation sweep cannot.

Leave the thresholds alone on a first run; the server's defaults are the conventional ones. Tighten a specific bound when chasing a specific class of error.

May run in the background, in which case a task_id comes back — poll it with get_job.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
tree_idNoTree to check. Leave empty to use the tree these credentials are bound to, which is the usual case.
max_spousesNoFlag more spouses than this. Server default 3.
estimate_ageNoEstimate missing or inexact dates when checking ages. Finds more, at the cost of guessing.
max_father_ageNoFlag a father older than this. Server default 65.
max_mother_ageNoFlag a mother older than this. Server default 48.
min_father_ageNoFlag a father younger than this. Server default 18.
min_mother_ageNoFlag a mother younger than this. Server default 17.
max_age_at_deathNoFlag a death later than this age. Server default 90.
max_age_to_marryNoFlag a marriage older than this. Server default 50.
min_age_to_marryNoFlag a marriage younger than this. Server default 17.
flag_invalid_datesNoReport dates the parser cannot read.
max_children_fatherNoFlag a man with more children than this. Default 15.
max_children_motherNoFlag a woman with more children than this. Default 12.
max_widowhood_yearsNoFlag a longer widowhood before remarriage. Default 30.
max_child_birth_spanNoFlag a longer span of one couple's births. Default 25.
max_husband_wife_age_gapNoFlag a wider spousal age gap. Server default 30.
max_years_between_childrenNoFlag a longer gap between siblings. Default 8.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A4.6/5.0
Behavior4/5

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

Annotations already declare readOnlyHint=true and openWorldHint=false, so safety is covered. The description adds genuinely new behavioral context: it may run in the background and return a task_id that must be polled with `get_job`. It does not mention result sizes or runtime expectations, keeping it just below 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?

Well front-loaded: purpose, differentiation, usage guidance, and async behavior in order. The illustrative examples earn their place, but the prose is slightly longer than strictly necessary for a read-only audit tool.

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?

For a 17-parameter, zero-required read-only tool with full schema coverage and no output schema, the description covers purpose, sibling routing, threshold strategy, and the async return contract. An agent has everything needed to invoke and poll 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%, so the 17 threshold parameters and their defaults are already fully documented, giving a baseline of 3. The description adds conceptual guidance beyond the schema — that defaults are conventional and bounds should only be tightened for targeted error classes — which meaningfully shapes how the agent sets them.

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 (run Gramps' plausibility checks over the whole tree) and immediately differentiates from the citation audit by naming `list_unsourced_facts` and contrasting evidence vs possibility. The examples (mother at nine, 120-year marriage, unparseable date) make the scope unmistakable.

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?

Explicitly says when to use this vs the sibling citation sweep, and gives operational guidance on configuration: leave thresholds at server defaults on a first run, tighten a specific bound when chasing a specific error class. Nothing 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