subagent-cockpit-mcp

Overview Schema Source Related Servers Discussions Admin

answer

Respond to an agent's pending question by accepting with schema-matched content, declining, or canceling, and optionally wait for the turn result.

Instructions

Answer a question the agent asked (question_needed). requested_schema is the agent's own form, passed on as sent: with action "accept" (the default), give content as an object whose keys and values follow it. "decline" refuses to answer, "cancel" dismisses the question. Blocks until the turn is done, needs an approval or asks a question; the server sets no time limit. If your client times out, the turn keeps running and the connection stays: call status for the state and output for the reply instead of sending the task again. Returns "approval_needed" with an approval to answer via approve / allow / reject, or "question_needed" with a question to answer via answer.

Input Schema

Name	Required	Description
`wait`	No	Wait for the result (default true). false returns right after sending.
`action`	No	accept (default), decline or cancel
`content`	No	Field values for accept: string, number, boolean or an array of strings
`session`	Yes	Session id returned by open
`question_id`	Yes	question_id from the question_needed result

Output Schema

Name	Required	Description	Default
`output`	No
`status`	Yes
`outcome`	No
`turn_id`	No
`approval`	No
`question`	No

Schema Changelog

Changes observed during successful MCP inspections.

First observedv0.2.1Oct 23, 2026

TDQS

A4.8/5.0

Behavior5/5

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 blocking behavior, no server time limit, timeout resilience with running turn, and the return state that triggers approval vs question. This is rich behavioral context beyond the schema.

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?

Purpose is front-loaded and most sentences earn their place, but the final sentence repeats return-state information already implied and the blocking sentence is dense.

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 5 parameters, nested content, and an output schema, the description covers critical operational details: blocking, timeout recovery, action semantics, and return-state branching. Nothing essential is missing.

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% (baseline 3), but the description adds meaning by linking content keys to requested_schema and clarifying action defaults and semantics beyond the schema's terse descriptions.

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+resource ('Answer a question the agent asked (question_needed)') and explicitly distinguishes itself from the approval flow (approve/allow/reject) and status/output alternatives for timeouts.

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 when to use it (question_needed), what each action does, and when to use alternatives (status/output on timeout instead of resending). Leaves no inference required.

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

Deploy Server