Skip to main content
Glama
muad-yasin

The High Council

by muad-yasin
OverviewSchemaSourceRelated ServersDiscussions(1)Admin
JavaScript
Remote

start_run

Launch a background harness run for planning, building, or grading tasks, returning a run ID for status polling. Configure it with a chain name and working-directory paths.

Instructions

Start a harness run in the background. Returns the run id to poll with run_status, or started:false with the exit code and log tail if the run stopped at once. chain is a chain name as list_chains shows it (never a path); leave it out to use the default chain, and the answer names it. task, draft, context and from_run are paths inside your working directory (tasks/x.md, context/my-project, runs/); anything outside it, or on the secret/credential denylist, is refused. draft + from_run + rounds=1 makes a panel-only grading pass.

Input Schema

NameRequiredDescriptionDefault
taskYes
chainNo
draftNopath to a draft to review instead of building one
roundsNo
contextNo
max_usdNothe figure to suggest as the run's spending limit, in USD, a positive number. For a paid chain the limit is the number the person types in the dialog; this figure is only the suggestion, and "none" is refused (nothing started). Left out, the dialog suggests MAX_USD_PER_RUN (a user who set COUNCIL_MAX_USD_LIMIT gets the lesser of the two, with $7 for an unset MAX_USD_PER_RUN); with neither set it suggests nothing. A chain with no paid seat has no dialog: there this figure is the run's ceiling ($7 when nothing sets it) and "none" removes it. A figure above COUNCIL_MAX_USD_LIMIT is refused, and so is "none" on a chain with no paid seat where the user set that limit; 0 is refused. The run stops cleanly before any stage that could pass its limit, and resumes with a higher total.
from_runNoreuse this earlier run's criteria
allow_unfencedNowaive the artifact gate: true for the whole task, or a list of file names that are only locations, not content the panel needs

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed4 schema fields changedv0.8.3
    • removedInput schema / properties / allow_secret_shaped
      Removed value: -{
-  "description": "send key-shaped text anyway. Every prompt is scanned for the key formats in src/secret-patterns.js before it leaves, and a match refuses the run (exit 11, started:false with the file, line and format in the log, never the value). Saved with the run, so resume_run keeps it. Off unless given.",
-  "type": "boolean"
-}
    • changedInput schema / properties / max_usd / description
      Previous value: -"per-run spend ceiling in USD, a positive number. Defaults to MAX_USD_PER_RUN or $7. Pass \"none\" for no ceiling (refused if the user set COUNCIL_MAX_USD_LIMIT); 0 is refused. The run stops cleanly before any stage that could breach it, and resumes with a higher ceiling."New value: +"the figure to suggest as the run's spending limit, in USD, a positive number. For a paid chain the limit is the number the person types in the dialog; this figure is only the suggestion, and \"none\" is refused (nothing started). Left out, the dialog suggests MAX_USD_PER_RUN (a user who set COUNCIL_MAX_USD_LIMIT gets the lesser of the two, with $7 for an unset MAX_USD_PER_RUN); with neither set it suggests nothing. A chain with no paid seat has no dialog: there this figure is the run's ceiling ($7 when nothing sets it) and \"none\" removes it. A figure above COUNCIL_MAX_USD_LIMIT is refused, and so is \"none\" on a chain with no paid seat where the user set that limit; 0 is refused. The run stops cleanly before any stage that could pass its limit, and resumes with a higher total."
    • removedInput schema / properties / pii_gate
      Removed value: -{
-  "description": "scan the task for PII and the key formats in src/secret-patterns.js before any provider call: warn logs and proceeds, hard-stop refuses the run. Off unless given.",
-  "enum": [
-    "warn",
-    "hard-stop"
-  ],
-  "type": "string"
-}
    • changedInput schema / required
      Previous value: -[
-  "chain",
-  "task"
-]New value: +[
+  "task"
+]
  2. First observedv0.8.1

TDQS

A4.3/5.0
Behavior4/5

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

With no annotations, the description carries the full burden and does real work: it discloses background execution, the dual success/failure return shape including exit code and log tail, and that out-of-scope or denylisted paths are refused. It omits that starting a run spends money and is not trivially reversible, which for a mutation tool with zero annotation coverage is a notable remaining gap.

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 action and return contract, then parameter guidance in descending importance; nearly every clause adds a constraint an agent would otherwise guess wrong. It is a dense block rather than a structured list, which makes the path-safety and panel-only rules slightly harder to scan.

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 8-parameter, annotation-free tool with no output schema, the description covers what is returned, the background lifecycle, path scoping, and one named use case. Remaining gaps are domain-vocabulary assumptions (harness, chain, panel, "artifact gate") that an agent unfamiliar with the product must infer from context.

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 coverage is 50%, and the description compensates on exactly the thin fields: chain is "a chain name as list_chains shows it (never a path)", task/draft/context/from_run are constrained to paths inside the working directory, and rounds interacts with draft+from_run. max_usd and allow_unfenced are left to their already-verbose schema descriptions, which is a reasonable division of labor.

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 and resource ("Start a harness run") plus the execution mode (background) and the return contract (run id or started:false). It also names the sibling that consumes the result (run_status) and the sibling that supplies chain names (list_chains), so an agent can place it among 22 siblings without opening a schema.

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 concrete selection rules: omit chain for the default, and "draft + from_run + rounds=1 makes a panel-only grading pass" is an explicit recipe for one mode. It does not state when to prefer dry_run or council_quote over actually starting a run, so it stops short of full when/when-not coverage.

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