Skip to main content
Glama
delimit-ai

delimit

Official
by delimit-ai
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Hybrid

Delimit Agent Handoff

delimit_agent_handoff

Transfer an active agent task to a different AI model when the current executor is blocked or cross-model review is needed, passing context and notes so the next model can continue.

Instructions

Hand off an agent task to a different AI model.

When to use: when an executor is blocked or when cross-model review is required and the next model needs the task's context. When NOT to use: to close out the task (delimit_agent_complete) or create a new one (delimit_agent_dispatch).

Sibling contrast: delimit_agent_complete ends the task; this transfers it to another model.

Side effects: writes a handoff record via ai.agent_dispatch.handoff_task; updates assignee on the task.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
contextNoNotes for the next model.
task_idYesExisting task id from delimit_agent_dispatch. Required.
to_modelYesExplicit target worker — "claude", "codex", "gemini", or "copilot". Copilot identifies a harness, not a model family. Required.

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault

No arguments

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changedv4.19.1
    • changedInput schema / properties / to_model / description
      Previous value: -"Target model — \"claude\", \"codex\", \"gemini\", etc. Required."New value: +"Explicit target worker — \"claude\", \"codex\", \"gemini\", or \"copilot\". Copilot identifies a harness, not a model family. Required."
  2. Changed3 schema fields changedv4.7.9
    • addedInput schema / properties / context / description
      Added value: +"Notes for the next model."
    • addedInput schema / properties / task_id / description
      Added value: +"Existing task id from delimit_agent_dispatch. Required."
    • addedInput schema / properties / to_model / description
      Added value: +"Target model — \"claude\", \"codex\", \"gemini\", etc. Required."
  3. Addedv4.5.5

TDQS

A4.7/5.0
Behavior5/5

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

Annotations already indicate this is a write operation (readOnlyHint: false), and the description goes further by naming the exact side effects: writing a handoff record via ai.agent_dispatch.handoff_task and updating the task's assignee. This gives the agent a clear model of the state changes it will trigger.

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, scannable sections with no wasted sentences. Every part earns its place: the action, when-to-use, when-not-to-use, sibling contrast, and side effects are all present without 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?

Given the small parameter set, full schema coverage, and presence of an output schema, the description covers everything an agent needs: purpose, valid invocation conditions, exclusions, and side effects. Nothing material is missing.

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 100%, so the schema already carries the full meaning of task_id, to_model, and context. The description adds only indirect context ('next model needs the task's context') and does not provide substantial extra parameter-level guidance beyond the schema.

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 specific verb and resource: 'Hand off an agent task to a different AI model.' It also explicitly contrasts with delimit_agent_complete and delimit_agent_dispatch, making it easy for an agent to distinguish this tool from its closest siblings.

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?

The 'When to use' section names concrete scenarios (executor blocked, cross-model review), and the 'When NOT to use' section explicitly routes to alternative tools. The sibling contrast reinforces the boundary, leaving no ambiguity about when to invoke this tool.

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