Skip to main content
Glama
Scormave

Gramps Web MCP

by Scormave
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Hybrid

Get Reference

get_reference
Read-only

Read reference guidance before writing Gramps Web data when formats or types are unclear, covering input rules, valid types, metadata, and name settings.

Instructions

Read the server's reference text before writing when a format or type is unclear. Topics: input-guide (how to write dates, names, link updates and structured fields such as attributes and addresses), types (the valid event, role, place, note and other types, including custom ones the tree uses), metadata (server and tree info), and name-settings (name display formats and surname groups). section narrows the reply to one part; an unknown topic or section is rejected with the valid ones. The same texts are MCP resources (gramps://input-guide and so on) for clients that read resources.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
topicYesWhich reference: input-guide, types, metadata or name-settings.
sectionNoOne part only (optional; omit for the whole topic). input-guide: dates, name_schema, link_updates, structured_fields, or one of structured_fields.names, .attributes, .urls, .addresses, .person_associations, .repository_refs. types: a category such as event_types or place_types. name-settings: formats or groups. metadata has no sections.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changedv2.3.0
    • changedInput schema / properties / section / description
      Previous value: -"Optional section. input-guide: dates | name_schema | link_updates | structured_fields | structured_fields.names | structured_fields.attributes | structured_fields.urls | structured_fields.addresses | structured_fields.person_associations | structured_fields.repository_refs. types: a category key such as event_types. name-settings: formats | groups. Not supported for metadata."New value: +"One part only (optional; omit for the whole topic). input-guide: dates, name_schema, link_updates, structured_fields, or one of structured_fields.names, .attributes, .urls, .addresses, .person_associations, .repository_refs. types: a category such as event_types or place_types. name-settings: formats or groups. metadata has no sections."
    • changedInput schema / properties / topic / description
      Previous value: -"Reference topic: input-guide | types | metadata | name-settings."New value: +"Which reference: input-guide, types, metadata or name-settings."
  2. First observedv2.2.0

TDQS

A4.1/5.0
Behavior4/5

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

Annotations already cover the safety profile (readOnlyHint=true, destructiveHint=false), so the bar is lower. The description adds genuinely useful behavior: section narrows the reply to one part, and an unknown topic/section is rejected with the valid ones listed. It also discloses that the same texts exist as resources.

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 primary instruction ('Read ... before writing'), followed by topic enumeration and the section caveat. It is dense and information-rich, though the topic list is slightly long relative to the action; every sentence still carries meaning.

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?

There is no output schema, but the description compensates by describing what each topic's text contains (date/name/link formats, valid type categories, server/tree info, name display settings). Return format isn't specified, but an agent has enough to call it correctly.

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 topic and section in detail, including valid section values per topic. The description restates the topic list and the section-narrowing behavior without adding format or syntax beyond the schema, so the baseline 3 applies.

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+resource (read the server's reference text) and enumerates exactly what it covers: input-guide, types, metadata, name-settings. This clearly distinguishes it from the write-focused siblings (create_*, update_*) and from get_object/get_timeline.

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 a clear trigger ('before writing when a format or type is unclear') and names an alternative access path (the same content is available as MCP resources). It stops short of saying when not to use it, but the intended context is unambiguous.

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