Skip to main content
Glama
Sign In
zai-one

grok-delegate

by zai-one
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Local

Plan only

grok_delegate_plan

Delegate a coding goal to Grok CLI for read-only planning; no write, edit, or shell mutations allowed.

Instructions

Read-only plan variant of grok_delegate (plan_only=true). Does not allow write/edit/shell mutation in the permission profile.

Input Schema

NameRequiredDescriptionDefault
cwdNoProject directory to work in; must be an allowlisted root
goalYesCoding goal for the executor
laneYesLane slug or grok/<slug> (not dev/master/main)
modelNoOptional model id
rulesNoOptional extra rules appended to system prompt (bounded)
resumeNoResume session: true for most recent, or a session UUID string
sandboxNoOptional sandbox profile override: off|workspace|devbox|read-only|strict (known built-ins only)
base_refNoGit base ref (default origin/dev)origin/dev
max_turnsNoMax agent turns (server hard-capped at 60)
plan_onlyNo
repo_rootNoAbsolute path to a repo root; accepted only if it resolve()s to an entry on GROK_DELEGATE_ALLOWED_ROOTS (or single GROK_DELEGATE_REPO_ROOT pin)
session_idNoUUID for --session-id (new or forked session name)
json_schemaNoOptional JSON Schema object/string for structured output
fork_sessionNoPass --fork-session (requires resume/continue)
lane_verdictNoAttach the lane verdict schema (default true). The run ends when the executor emits that object, so on a goal it must read the codebase to start, it emits one describing intent and the lane closes empty. Set false for exploration-heavy goals: the executor then works to natural completion and reports prose in summary instead of a parsed verdict.
lanes_parentNoOptional parent dir for worktrees; rejected if inside repo_root or outside GROK_DELEGATE_LANES_PARENT when that env is set
no_subagentsNoIf true, pass --no-subagents
continue_sessionNoPass --continue (most recent for cwd)
reasoning_effortNoOptional reasoning effort (low|medium|high|…)
disable_web_searchNoIf true, pass --disable-web-search

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changedv0.26.1
    • addedInput schema / properties / cwd
      Added value: +{
+  "description": "Project directory to work in; must be an allowlisted root",
+  "type": "string"
+}
  2. First observedv0.4.1

TDQS

A3.5/5.0
Behavior3/5

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

Annotations already declare the safety profile (readOnlyHint=false, destructiveHint=false, openWorldHint=true). The description adds genuine non-obvious context by scoping 'read-only' to the permission profile ('does not allow write/edit/shell mutation'), but says nothing about what the call actually creates (sessions, worktrees) or its execution model. Note the tension: the phrase 'Read-only plan variant' sits awkwardly against readOnlyHint=false, though it is explicitly scoped to the executor's permission profile rather than the tool's own side effects.

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?

Two tight sentences, front-loaded with the distinguishing fact and the mechanism, with zero filler. Every clause earns its place.

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 20-parameter open-world delegation tool this is thin, but 95% schema coverage and present annotations carry most of the load. The core distinction from grok_delegate is covered; output/artifact behavior and session semantics are left to the schema.

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 95% across 20 params, so the schema already carries parameter meaning; baseline 3 applies. The description only echoes plan_only=true, adding no syntax, format, or interaction detail beyond the structured fields.

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?

States a specific variant of a specific tool ('Read-only plan variant of grok_delegate') and pins the mechanism ('plan_only=true'), which cleanly separates it from the write-capable grok_delegate sibling. It clearly conveys that this produces a plan rather than mutations. It stops short of a crisp verb+object statement but is unambiguous.

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?

The framing 'plan variant of grok_delegate' implies when to reach for it (planning vs execution) but never states it explicitly, names no prerequisites, and gives no exclusions. Usage is inferable only by contrast with the sibling name.

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