Skip to main content
Glama
rnd-pro
by rnd-pro

delegate_task_readonly

Delegate read-only analysis tasks to a CLI agent for code review, bug detection, and report generation. Returns a task ID immediately; use get_task_result to retrieve results asynchronously.

Instructions

Delegate a read-only analysis task to a CLI agent. The agent is sandboxed to cwd directory only. Use include_dirs to grant access to additional directories. It is semantically identical to delegate_task but signals that the task is primarily for analysis. Use this for code review, architecture analysis, finding bugs, writing reports, etc.

Returns a task_id immediately (non-blocking). Use get_task_result to check status and retrieve the result.

IMPORTANT: CLI providers can take ~15-20s before the agent begins working. Set timeout to at least 60s for simple tasks, 300s+ for complex analysis. WORKSPACE: The agent can only use file tools within cwd and include_dirs. For other paths it can use shell commands (cat, find, ls).

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
cwdNoWorking directory. Defaults to current working directory.
filesNoKnown relevant file paths used as structured focus hints for context resolution. May include paths attached in the UI.
modelNoModel to use in provider/model format (e.g. deepseek/deepseek-v4-pro). Leave empty for default.
promptYesThe analysis task for the CLI agent.
runnerNoRunner ID from agent-pool.config.json. Default: "local". Use SSH runners for remote execution.
chat_idNoThe chat ID created for this task via create_chat. Optional.
timeoutNoTimeout in seconds. Default: 600 (10 minutes).
providerNoCLI provider to use. codex = Codex CLI, antigravity = Antigravity CLI, opencode = OpenCode CLI, claude = Claude Code CLI. Default: codex.
agent_slugNoAgent identity slug (e.g. "code-reviewer"). Auto-resolves prompt from team-memory agents/{slug}.md.
session_idNoResume an existing provider session/thread by ID. Supported by Antigravity, Codex, OpenCode, and Claude Code where available. Use list_sessions for Antigravity sessions.
focus_graphNoPortal-provided compact project-graph focus context for files[], including symbols, imports, dependencies, and web component summaries when present. Usually injected automatically; direct callers should prefer files[].
serviceTierNoService tier for Codex. Codex maps to service_tier.
context_modeNoContext package mode for delegated agents. auto injects the metadata-first resolved context package. off disables injection. Default: auto.
include_dirsNoAdditional directories to include in the agent workspace scope. By default the agent only has access to cwd.
on_wait_hintNoCustom coaching message shown when polling for results.
system_promptNoPre-resolved system prompt to prepend to the task. Overrides agent_slug resolution.
parent_chat_idNoThe parent chat or task ID that initiated this delegation. Used for hierarchy. Optional.
resource_groupNoExisting resource group from local portal configuration. Overrides the agent frontmatter resource_group.
reasoningEffortNoProvider reasoning effort. Codex accepts the selected model value and maps it to model_reasoning_effort. Claude Code accepts low, medium, high, xhigh, or max and maps it to --effort.
Behavior5/5

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

No annotations provided, so the description carries full burden. Discloses non-blocking nature, provider startup delay, workspace restrictions (cwd + include_dirs), and that shell commands can access other paths. Also explains similarity to delegate_task.

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?

Well-structured with purpose first, then behavior, then important notes. Slightly long but all information is relevant and no redundancy.

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?

Given 19 parameters and no output schema, the description explains return behavior, workspace, timing, and provider options. It is sufficiently complete for correct tool invocation.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters5/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100% with all parameters described. The description adds value by explaining workspace behavior and recommending use of include_dirs, complementing the schema details.

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?

The description clearly states 'Delegate a read-only analysis task to a CLI agent' and distinguishes itself from the sibling 'delegate_task' by noting it is semantically identical but signals analysis intent.

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?

Provides explicit use cases (code review, architecture analysis, etc.), mentions how to retrieve results with get_task_result, and gives timeout recommendations. However, it does not explicitly state when to prefer delegate_task over this tool.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Install Server

Other Tools

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/rnd-pro/agent-pool-mcp'

If you have feedback or need assistance with the MCP directory API, please join our Discord server