Skip to main content
Glama
Sign In
littlebigbrains

@littlebigbrain/mcp

by littlebigbrains
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Hybrid

lbb_embeddings_manage

Declare or refresh knowledge graph embeddings, preview embedded text and fields, or move a graph to a new embedding model with versioned handoff.

Instructions

Declare or refresh an embedding, or change the graph's model. Run lbb_embeddings action=preview first and show the user the text it will embed. declare sets the class, the fields (one-hop property paths such as label, description, calls/label; omit for an automatic choice); a new embedding takes the graph's model, and another model is refused. On an existing embedding it changes only what you name, and a changed recipe builds a new version while the old one serves. model moves every embedding of the graph to model: each builds a new version, and the graph switches when all are ready (a search never mixes two models). refresh runs one step of the embed job now (it also runs by itself after each published commit).

Input Schema

NameRequiredDescriptionDefault
dimNo
fromNopreview/declare: the fields, e.g. ["label", "description", "calls/label"]. Omit for the automatic choice; on an existing embedding, omit to keep its fields.
nameNoThe embedding name (refresh: required).
classNopreview/declare: the class IRI.
graphNoGraph to target; defaults to the connection's graph
modelNomodel: the graph's new model. preview/declare: omit it; a graph has one model (the graph's, or the platform's default for the first embedding).
titleNopreview/declare: the field that names each hit, e.g. "display_name". Omit for the ontology's name property (skos:prefLabel, a property declared rdfs:subPropertyOf rdfs:label, else rdfs:label); on an existing embedding, omit to keep its name. preview reports title_source and, when the labels read as keys, title_suggestion.
actionYes
detailNoResponse detail level. Defaults to compact.
excludeNopreview/declare: fields to drop from the automatic choice.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changedv0.16.0
    • removedInput schema / additionalProperties
      Removed value: -false
    • addedInput schema / properties / dim / maximum
      Added value: +9007199254740991
  2. Addedv0.5.2

TDQS

A4.5/5.0
Behavior5/5

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

Annotations only declare this is a non-read-only, non-destructive, closed-world write; the description adds substantial behaviour beyond that: a changed recipe builds a new version while the old one keeps serving, model switching is deferred until every embedding is rebuilt so 'a search never mixes two models,' and refresh executes exactly one step of the embed job that otherwise runs automatically after each published commit. It also imposes a human-in-the-loop confirmation requirement absent from any structured field.

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?

The capability statement is front-loaded and every sentence carries operational content rather than filler. It is a dense single block, though, and the versioning/model-switch sentences are long enough that an agent must parse carefully to separate per-action rules.

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 10-parameter mutation with no output schema, the description covers ordering, versioning, job execution and model immutability rules well. The notable gap is the `dim` parameter, which has neither a schema description nor any mention in the prose, so an agent gets no guidance on when a dimension must be supplied.

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?

With 80% schema coverage the baseline is 3, and the description earns more by explaining semantics the schema does not: one-hop property path syntax for fields, that omitting fields on an existing embedding preserves them, and the constraint that a new embedding must adopt the graph's model while any other model is refused. It leaves `dim` and `graph` entirely unaddressed, which are the two weakest-documented parameters.

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 set and resource: 'Declare or refresh an embedding, or change the graph's model.' The three action values (declare/refresh/model) are each distinguished from one another and from the read-only sibling lbb_embeddings, which is named explicitly.

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 prerequisite workflow: 'Run lbb_embeddings action=preview first and show the user the text it will embed,' which routes the agent to the sibling before writing. It also explains what each action does so the agent can pick one. It stops short of stating when this tool should not be used at all.

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