Skip to main content
Glama
littlebigbrains

@littlebigbrain/mcp

by littlebigbrains
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Hybrid

lbb_models

Read-only

Read model-training inputs, compare retrieval configurations on one pinned snapshot, and inspect monthly model usage, calls, tokens, and costs by feature.

Instructions

Read model-training inputs or compare retrieval configurations over one pinned published snapshot, or read what the managed models did. shadow_eval takes the API ShadowEvalRequest body; dataset actions return bounded training examples at an optional signal split. activity reads one month of the stack's model use (all graphs): calls, items, estimated tokens and cost per feature (index, search, fit, judge, training) and model, by day and by graph, the months with activity, and the model each feature uses now.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
bodyNo
graphNoGraph to target; defaults to the connection's graph
limitNo
monthNoactivity: the month, yyyy-mm (UTC). Defaults to the current month.
actionYes
detailNoResponse detail level. Defaults to compact.
split_seqNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changedv0.9.0
    • changedInput schema / properties / action / enum
      Previous value: -[
-  "shadow_eval",
-  "suggest_dataset",
-  "extractor_dataset"
-]New value: +[
+  "shadow_eval",
+  "suggest_dataset",
+  "extractor_dataset",
+  "activity"
+]
    • addedInput schema / properties / month
      Added value: +{
+  "description": "activity: the month, yyyy-mm (UTC). Defaults to the current month.",
+  "pattern": "^\\d{4}-(0[1-9]|1[0-2])$",
+  "type": "string"
+}
  2. Changed1 schema field changedv0.6.0
    • changedInput schema / properties / action / enum
      Previous value: -[
-  "shadow_eval",
-  "planner_dataset",
-  "planner_preference_dataset",
-  "suggest_dataset",
-  "extractor_dataset"
-]New value: +[
+  "shadow_eval",
+  "suggest_dataset",
+  "extractor_dataset"
+]
  3. Changed1 schema field changedv0.5.2
    • removedInput schema / properties / branch
      Removed value: -{
-  "description": "Branch to target; defaults to the connection's branch",
-  "type": "string"
-}
  4. Addedv0.2.7

TDQS

A3.5/5.0
Behavior4/5

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

Annotations declare readOnlyHint=true and the description is consistent, framing everything as reads. It goes beyond the annotation by disclosing return content shape: bounded training examples, a one-month window, and per-feature/per-model/per-day cost and token breakdowns. It does not cover pagination or default detail behavior beyond what the schema states.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness3/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The opening sentence front-loads the tool's scope well, but the final sentence is a long comma-chained run-on enumerating features, dimensions, and defaults, which is harder to parse than necessary. Information density is high, but structure could be tightened with per-action sentences or a list.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a 7-parameter multiplexed tool with no output schema and 43% schema coverage, the description covers the action semantics reasonably but leaves required agent knowledge gaps: graph targeting, limit behavior, and detail-level effects are unexplained, and no return envelope for shadow_eval is described.

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 only 43%, so the description must compensate. It does explain `body` (ShadowEvalRequest for shadow_eval), implies `split_seq` via 'at an optional signal split', and covers `month` semantics for activity, but leaves `graph`, `limit`, and `detail` to the schema, which documents only the first two.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description names concrete verbs and resources: reading model-training inputs, comparing retrieval configurations over a pinned published snapshot, and reading managed-model activity. It separates the four action modes (shadow_eval, the two dataset actions, activity) so an agent can tell what the tool covers, though it never contrasts itself against the similarly named lbb_evals or lbb_query siblings.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

It implies usage per action (shadow_eval takes an API ShadowEvalRequest body; dataset actions return bounded training examples at a signal split; activity reads one month of model use), which helps pick an action value. However, there is no guidance on when to choose this tool over sibling tools like lbb_evals or lbb_query, and no stated prerequisites.

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