Skip to main content
Glama

handoff_send

Hand off errands, questions, or status updates to the user's personal agent as a desk note; configured channels alert the agent, and replies land in the note.

Instructions

Hand a task to the user's personal agent. It lands as a note in the desk folder (pushed to the shared repository when the desk syncs through git) and the agent is notified by the doorbells that are configured (email, and optionally Telegram or Slack); the agent answers in the note. notified lists the doorbells that rang. If it is empty, nobody has been told yet: send ring's email by another route (for example a mail connector). Use for errands outside the computer, questions while the user is away, and status lines; never for building or code work. Never include passwords, codes or keys.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "type": "<type>",
      "title": "<title>",
      "request": "<request>"
    },
    "name": "handoff_send"
  }
}

Input Schema

NameRequiredDescriptionDefault
typeYes
titleYes
replyByNo
requestYesWhat is needed and why, plus any deadline

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv1.0.0

TDQS

A4.3/5.0
Behavior4/5

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

Beyond the annotations it discloses the full side-effect chain: the task becomes a persisted note in the desk folder, reaches the shared repository on the next git sync, and triggers configured doorbells. It also explains a return signal (`notified`) despite the absence of an output schema, and issues a data-hygiene warning against including passwords, codes or keys. It does not state that repeat calls create duplicate notes (non-idempotence), which is the main remaining behavioral gap.

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 and delivery mechanism are front-loaded, and every sentence carries information: mechanism, return field, fallback, selection criteria, safety rule. It is dense but efficient; the parenthetical asides about git sync and doorbells make sentences slightly run-on, but nothing is redundant.

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 mutation tool with no output schema, the description covers side effects, notification behavior, the failure mode of an empty `notified`, and the security constraint. The gaps are the unexplained `replyBy`/`title` parameters and whether any handle or identifier is returned that later calls to handoff_answer/handoff_read would need.

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?

With only 25% schema description coverage, the description does useful work by mapping the `type` enum to real intent ("errands", "questions", "status lines"). However, it adds nothing about `title` or `replyBy`; `replyBy` in particular is ambiguous (deadline? response channel?) and is left to the bare 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 concrete verb and resource ("Hand a task to the user's personal agent") and immediately specifies the delivery mechanism (a note in the desk folder, pushed via git sync) and the notification path (doorbells: email, optionally Telegram/Slack). It is clearly distinguishable from read/answer siblings such as handoff_answer and handoff_inbox, which do not create notes.

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?

It gives explicit intended cases ("errands outside the computer, questions while the user is away, and status lines") and an explicit exclusion ("never for building or code work"). It also supplies a fallback procedure when the `notified` set comes back empty: route the email through another connector. That is when-to-use, when-not-to-use, and remediation in one pass.

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