Skip to main content
Glama
loncadev

Baron

by loncadev
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Remote

baron_recipe_run

Execute a named recipe as one deterministic workflow. Supply required inputs to run start-to-finish, or resume a failed run with its runId to continue without repeating completed steps.

Instructions

Run a named recipe end-to-end as ONE deterministic, rule-enforced workflow (the engine — not you — enforces the step order). Supply all required inputs (from baron_recipe_list) in inputs; a missing required input errors rather than prompting. Prefer this over composing the individual issue/scm/ci tools yourself for a packaged workflow. Returns the run context as JSON (with its runId), and — when the recipe had anything to say — a SECOND text block with its messages. Read that block: it is where a recipe reports what it could not verify (task-land warns there when it merged past checks it could not see). Every run is journaled: if one fails partway, do NOT run it again from scratch (that repeats the steps that already mutated the provider — a second PR). Call this with resume: <runId> from the error instead: completed steps are replayed from the journal and the run carries on from where it stopped.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
nameNoRecipe name (e.g. task-start). Required unless `resume` is given.
inputsNoValues for the recipe's `ask` inputs, keyed by input name.
resumeNoThe `runId` of a run that stopped (from its error, under details.run.id): continue it instead of starting a new one. Its inputs and answers are restored from the journal.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed3 schema fields changedv0.41.0
    • changedInput schema / properties / name / description
      Previous value: -"Recipe name (e.g. task-start)."New value: +"Recipe name (e.g. task-start). Required unless `resume` is given."
    • addedInput schema / properties / resume
      Added value: +{
+  "description": "The `runId` of a run that stopped (from its error, under details.run.id): continue it instead of starting a new one. Its inputs and answers are restored from the journal.",
+  "minLength": 1,
+  "type": "string"
+}
    • removedInput schema / required
      Removed value: -[
-  "name"
-]
  2. First observedv0.1.0

TDQS

A4.9/5.0
Behavior5/5

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

No annotations are provided, so the description carries the full burden. It discloses that missing required inputs error rather than prompting, that the return includes both run context JSON and a second message block, that every run is journaled, and that resume replays completed steps. It also warns about repeated mutations causing 'a second PR'.

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

Conciseness5/5

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

The description is long but every sentence earns its place: purpose, input requirements, alternatives, return shape, message-block reading instruction, failure warning, and resume path are all packed into a compact narrative. It is front-loaded with the core purpose and goes deeper only where operational safety demands it.

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?

With no output schema and no annotations, the description needed to explain return values and failure behavior, and it does. It covers how to obtain the recipe inputs, what the run returns, where to look for unverified information, and how to recover after a partial failure. It is sufficiently complete for an agent to select and safely invoke this tool.

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?

The schema already documents all 3 parameters with 100% coverage, but the description adds operational semantics beyond the schema: inputs must be supplied from baron_recipe_list, missing required inputs error rather than prompt, and resume restores inputs and answers from the journal. This is valuable added meaning.

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 action, 'Run a named recipe end-to-end', and frames it as ONE deterministic, rule-enforced workflow where the engine enforces step order. It clearly distinguishes from siblings such as baron_recipe_list and from composing the individual issue/scm/ci tools.

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 to prefer this over composing the individual issue/scm/ci tools yourself, and gives a concrete when-not-to guidance: if a run fails, do NOT re-run from scratch, use resume with the runId from the error. This is strong usage direction beyond just stating what the tool does.

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