Skip to main content
Glama
littlebigbrains

@littlebigbrain/mcp

by littlebigbrains
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Hybrid

lbb_workflows_manage

Create a workflow from a starter workflow, or refresh, pause or resume a triggered workflow. Run lbb_workflows action=preview first and show the user the watch and the instance count.

Instructions

Create a workflow from a starter workflow, or refresh, pause or resume a triggered workflow. Run lbb_workflows action=preview first and show the user the watch and the instance count. use creates a workflow from a starter workflow of action=starters, under a name (default: the class's local name), with its watch (class, fields) and params; the workflow then reads every instance of the class and follows each published commit. A developer workflow (starter=workflow) also takes workflow (workflow_type and version of the developer's worker), owns and batch; it needs a server with the workflow engine. use again with the same starter and name changes only what you name, and the same request again changes nothing. A workflow that calls models (ontology.fit, documents.link, documents.map, values.extract) spends model budget as it reads. refresh asks the workflow to run now and returns at once with queued; poll lbb_workflows action=get for progress. pause stops a workflow (a developer workflow, documents.parse, documents.link, documents.map or values.extract) from reading and sending, and stops the claims of a developer workflow's shards; resume lets it catch up. Without starter, pause and resume name a workflow with triggers. search.embed and ontology.fit cannot be paused. define creates or changes a workflow with triggers of the developer's worker (/v1/workflows/named): name, workflow, class and fields (its watch trigger), owns, batch, and shards (engine identities, 1 to 16), route_by (a field that keeps work in order) and window (messages queued per shard, default 4); it needs a server with the workflow engine, and a change of shards waits for empty inboxes. run (name) runs a workflow with triggers now: its watch sends every instance again.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
gateNouse: outputs below this confidence go to review instead of the graph, for a workflow with a review gate.
nameNoThe triggered workflow's name, [a-z0-9][a-z0-9-]{0,62} (refresh, pause, resume: required; use: omit for the class's local name).
ownsNopreview/use, developer workflow only: what your code writes. classes it creates instances of, relations it writes as out-edges of the watched instances, properties it writes on them. Owned outputs never trigger the workflow itself.
batchNopreview/use, developer workflow only: instances per message, 1 to 64 (default 16).
classNopreview/use: the class whose instances the workflow watches (an IRI, or a name the ontology knows). Required unless the starter workflow's watch is fixed.
graphNoGraph to target; defaults to the connection's graph
actionYes
detailNoResponse detail level. Defaults to compact.
fieldsNopreview/use: the fields whose change triggers the workflow, as embedding paths (transcript, label, about/label, <https://…>). Omit for the starter workflow's own choice.
paramsNopreview/use: the starter workflow's own settings, as listed in its catalog entry: search.embed takes model, dim and title; ontology.fit takes context (one sentence about the text, e.g. {"context": "interviews with employees"}); workflow takes none.
shardsNodefine: engine identities that receive the messages, 1 to 16 (default 1). A change needs every shard's inbox empty.
windowNodefine: messages the watch keeps queued per shard, 1 to 128 (default 4).
excludeNopreview/use: fields to drop from the automatic choice.
starterNoThe starter workflow's catalog id from action=starters, e.g. search.embed (embeddings on a class), ontology.fit (fit from text) or workflow (a developer workflow: your worker's workflow gets the instances). get/preview/use/refresh: required. pause/resume: omit to name a workflow with triggers.
triggerNodefine: the watch trigger's id (default watch). queue: the trigger whose queue to read.
route_byNodefine: a field of the class whose value keeps work in order: the changes of one value go to one shard. Default: the instance.
workflowNopreview/use, developer workflow (starter=workflow) only, required there: the workflow of your worker that receives the messages. Creating it creates the instance starter.<name>.
budget_usd_per_monthNouse: a monthly model budget in USD for this workflow, below the stack's own.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Addedv0.14.0

TDQS

A4.1/5.0
Behavior5/5

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

The annotations only say this is a non-read-only, non-destructive, non-open-world tool; the description adds substantial behavioral facts beyond that: 'refresh ... returns at once with queued', workflows that call models 'spend model budget as it reads', 'pause ... stops the claims of a developer workflow's shards', and 'a change of shards waits for empty inboxes'. These are exactly the operational traits an agent needs and cannot infer from the schema or annotations.

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 purpose is front-loaded, but the body is a dense, semicolon-chained wall of text packed with six actions' worth of detail and no headings or bullet structure, making it hard to scan. Most sentences do carry information, so it is not padding, but the presentation hurts usability.

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 an 18-parameter, six-action tool with no output schema, the description covers each action, its key parameters, and the handoff to lbb_workflows for progress polling. It leaves some response shapes (use/define results) unspecified, but with no output schema and a coverage-rich input schema the remaining gap is minor.

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 description coverage is already 94%, so the 3 baseline applies, but the description adds real semantics not present in the schema: idempotency ('use again with the same starter and name changes only what you name, and the same request again changes nothing'), which parameters bind to which action, and what gate/budget imply. It does not cover every one of the 18 parameters, so it is not a 5.

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 states concrete verbs and the resource they act on for each mode: 'use' creates a workflow from a starter, 'refresh' runs it now, 'pause'/'resume' control it, 'define' creates or changes a triggered workflow, 'run' runs it. It implicitly distinguishes itself from the read-side sibling (lbb_workflows) by routing to it for preview/get. A sibling-specific exclusion is not spelled out, so it stops short of a 5.

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?

It gives an explicit prerequisite workflow: 'Run lbb_workflows action=preview first and show the user the watch and the instance count.' It also distinguishes pause/resume with vs. without a starter and notes exceptions ('search.embed and ontology.fit cannot be paused'). It never states when *not* to reach for this tool versus lbb_workflows_delete or lbb_workflows, so it is clear context without full exclusions.

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