delimit

Official

Overview Schema Source Related Servers Discussions Admin

Delimit Agent Answer

delimit_agent_answer

Answer a bound worker question to resume its session and keep the task on track, distinguishing routine from owner-backed answers.

Instructions

Answer a bound worker question and resume its muse session.

When to use: after delimit_agent_poll binds a worker QUESTION: block (question_id + receipt_id) to the task. The lead answers routine technical questions directly (owner_backed=False); only pass owner_backed=True when the answer carries a reserved owner decision. For muse workers the SAME session is resumed with the answer as its prompt file, so question → answer → task stays bound even if the lead process was replaced. When NOT to use: to ask the worker something new (that is a fresh dispatch), to close the task (use delimit_agent_complete), or to abort the worker (use delimit_agent_cancel). Do not answer twice — the backend rejects a second answer to the same question_id.

Sibling contrast: delimit_agent_poll surfaces the question; this resolves it. delimit_agent_status shows the waiting question and its receipt; delimit_agent_complete closes the task after the resumed worker finishes.

Side effects: persists the answer on the question record (owner_backed recorded exactly as given, never inferred), acknowledges the question's handoff receipt with the answer text, and — for muse tasks whose worker already reached completed/uncertain — resumes the SAME session via the contained launcher with the answer as the prompt file (a fresh output prefix per resume; prior transcripts preserved). No relaunch happens while the worker is still running.

Input Schema

TableJSON Schema

Name	Required	Description
`answer`	Yes	Answer text for the worker. Required.
`task_id`	Yes	Task id carrying the bound question (AGT-xxx). Required.
`question_id`	Yes	Question id from delimit_agent_poll (Q-xxx). Required.
`owner_backed`	No	If True, the answer carries an owner decision. Default False (routine lead answer).

Output Schema

TableJSON Schema

Name	Required	Description	Default
No arguments

Schema Changelog

Changes observed during successful MCP inspections.

Addedv4.19.1Sep 15, 2026

TDQS

A4.9/5.0

Behavior5/5

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

Annotations only mark readOnlyHint=false and destructiveHint=false. The description goes far beyond that, detailing side effects: persisting the answer, acknowledging the receipt, resuming the same muse session with the answer as a prompt file, fresh output prefixes, preserved transcripts, and the backend rejection of duplicate answers. This is rich, actionable behavioral context.

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?

The description is organized into clear labeled sections (When to use, When NOT to use, Sibling contrast, Side effects). The main purpose is front-loaded, and every sentence contributes necessary operational detail. It's long because the tool is complex, but there is zero fluff.

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?

For a tool with an output schema and complex workflow, the description covers all essential aspects: the trigger, the owner_backed decision, what happens on the backend, the muse session resume behavior, and explicit exclusions. An agent has everything needed to invoke it correctly without guessing.

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 all parameters are documented. The description adds meaningful context for owner_backed (only when a reserved owner decision is carried) and clarifies that the answer text is persisted. It doesn't invent new parameter meaning but does enrich the decision on owner_backed, earning a 4 over the baseline 3.

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 opens with a precise verb+resource statement: 'Answer a bound worker question and resume its muse session.' It then contrasts with sibling tools (poll, status, complete), making the tool's unique role unmistakable even before reading the 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?

Explicit 'When to use' and 'When NOT to use' sections spell out the exact trigger (after delimit_agent_poll binds a question), the condition for owner_backed=True, and name the alternatives (delimit_agent_complete, delimit_agent_cancel) for other scenarios. No inference is required.

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

Deploy Server