Skip to main content
Glama
plartex

agent-shuttle-mcp

by plartex
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Local

ask_agent

Delegate research, code review, implementation or a second opinion to a local AI agent: Antigravity (antigravity), Codex (codex), OpenCode (opencode), Claude Code (claude_code), or an agent_id from list_agents.

Instructions

Delegate research, code review, implementation or a second opinion to a local AI agent: Antigravity (antigravity), Codex (codex), OpenCode (opencode), Claude Code (claude_code), or an agent_id from list_agents. Делегирование: исследование, ревью, реализация, второе мнение. Use for an actual request to have another agent perform work. Answer general explanations and advice directly; mentioning an agent or a second opinion alone does not request delegation. Shuttle manages local servers automatically. Inspect get_agent_info before selecting an enforceable tool policy; research including web access depends on that agent's capabilities. For Antigravity web research choose web_research when advertised; read_only allows local files only. Preserve the user's explicit agent and model. Use submit_task for long work.

Input Schema

NameRequiredDescriptionDefault
modelNoExact remote model ID explicitly requested by the user; otherwise omit. Inspect get_agent_info for live models.
promptYesComplete delegated task, supplied context, constraints and requested output.
agent_idYesTarget: codex, antigravity, opencode, claude_code, or a configured agent_id from list_agents.
workspaceNoExisting absolute directory on the local host for the delegated task; otherwise use the server's configured workspace.
tool_policyNoLeast sufficient supported policy: no_tools, read_only, workspace_write, web_research (Antigravity native web tools only), or full_access (unrestricted tools; requires user authorization). Antigravity read_only cannot access the web. Inspect get_agent_info first.
reasoning_effortNoUser-requested remote reasoning effort; otherwise omit. Inspect supported values using get_agent_info.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed6 schema fields changedv0.8.2
    • addedInput schema / properties / agent_id / description
      Added value: +"Target: codex, antigravity, opencode, claude_code, or a configured agent_id from list_agents."
    • addedInput schema / properties / model / description
      Added value: +"Exact remote model ID explicitly requested by the user; otherwise omit. Inspect get_agent_info for live models."
    • addedInput schema / properties / prompt / description
      Added value: +"Complete delegated task, supplied context, constraints and requested output."
    • addedInput schema / properties / reasoning_effort / description
      Added value: +"User-requested remote reasoning effort; otherwise omit. Inspect supported values using get_agent_info."
    • addedInput schema / properties / tool_policy / description
      Added value: +"Least sufficient supported policy: no_tools, read_only, workspace_write, web_research (Antigravity native web tools only), or full_access (unrestricted tools; requires user authorization). Antigravity read_only cannot access the web. Inspect get_agent_info first."
    • addedInput schema / properties / workspace
      Added value: +{
+  "anyOf": [
+    {
+      "type": "string"
+    },
+    {
+      "type": "null"
+    }
+  ],
+  "default": null,
+  "description": "Existing absolute directory on the local host for the delegated task; otherwise use the server's configured workspace.",
+  "title": "Workspace"
+}
  2. First observedv0.5.0

TDQS

A4.4/5.0
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 well: it discloses that Shuttle manages local servers automatically, that research/web access depends on the selected agent's capabilities, that read_only allows local files only and blocks web for Antigravity, and that full_access requires user authorization. It omits what happens after the call (whether it blocks/returns a result or requires get_result), which is the main 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.

Conciseness3/5

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

Front-loaded and dense with useful constraints, but the Russian sentence 'Делегирование: исследование, ревью, реализация, второе мнение' duplicates the English purpose list and earns no place, and several policy caveats are packed into one long paragraph.

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 a 6-parameter delegation tool with no annotations and no output schema, the description covers target selection, safety policies, routing to siblings, and user authorization expectations. It stops short of explaining the call's lifecycle (sync vs async, how results are retrieved), which is the main item an agent might still need.

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 100%, so the baseline is 3, but the description adds selection guidance beyond the schema: inspect get_agent_info before selecting an enforceable tool policy, preserve the user's explicit agent and model, choose web_research for Antigravity web research, and use least sufficient policy. These add real decision meaning to agent_id and tool_policy.

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 precise verb and resource ('Delegate research, code review, implementation or a second opinion to a local AI agent') and enumerates the concrete targets (antigravity, codex, opencode, claude_code, configured agent_id). An agent can distinguish this from ask_antigravity/ask_codex and from list_agents/get_agent_info without opening any schema.

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 states when to use ('for an actual request to have another agent perform work') and when not to ('Answer general explanations and advice directly; mentioning an agent or a second opinion alone does not request delegation'). It also names the alternative for long-running work ('Use submit_task for long work') and instructs preserving the user's explicit agent/model.

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