Skip to main content
Glama

vibe_dm

Send a direct message to any developer on /vibe. Your message arrives immediately if they are online, or waits until their next session, so no one needs to be present to receive it.

Instructions

Send a direct message to someone on /vibe. It lands in their session now if they're around, or waits for their next turn — nobody has to be online. Sends exactly the text you give it; /vibe doesn't attach repository or session context.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
handleYesWho to message (e.g., @alex)
originNoHow this message came to be. Omit for a normal message you're composing. Pass the value the drafting tool told you to use when sending a draft it produced: 'intro' (vibe_intro), 'stuck_solver' (vibe_weave solve), 'held_half' (a Fable-held reply), 'fable'.
messageNoYour message
payloadNoOptional structured data (game state, code review, handoff, etc.)
reply_toNoOptional: Message ID to reply to (creates a threaded reply)
artifact_slugNoOptional artifact slug to share (e.g., "pizza-guide-abc123"). The artifact will be shown as a rich card.
approved_sha256NoOptional (#392): hex SHA-256 over UTF-8 of "<recipient> <message>" — recipient lowercased without a leading @, message trimmed — binding this send to exactly what the person approved. The server refuses a send that would store anything different. Drafting tools set it.
idempotency_keyNoOptional: a stable key for this exact send, so a retry delivers once. Drafting tools set it; omit when composing by hand.
tip_amount_centsNoOptional: Attach an instant USDC tip (100 = $1, 500 = $5, 1000 = $10)

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changedv0.8.27
    • addedInput schema / properties / approved_sha256
      Added value: +{
      +  "description": "Optional (#392): hex SHA-256 over UTF-8 of \"<recipient>\n<message>\" — recipient lowercased without a leading @, message trimmed — binding this send to exactly what the person approved. The server refuses a send that would store anything different. Drafting tools set it.",
      +  "type": "string"
      +}
    • addedInput schema / properties / idempotency_key
      Added value: +{
      +  "description": "Optional: a stable key for this exact send, so a retry delivers once. Drafting tools set it; omit when composing by hand.",
      +  "type": "string"
      +}
  2. Changed6 schema fields changedv0.8.18
    • addedInput schema / properties / artifact_slug
      Added value: +{
      +  "description": "Optional artifact slug to share (e.g., \"pizza-guide-abc123\"). The artifact will be shown as a rich card.",
      +  "type": "string"
      +}
    • addedInput schema / properties / origin
      Added value: +{
      +  "description": "How this message came to be. Omit for a normal message you're composing. Pass the value the drafting tool told you to use when sending a draft it produced: 'intro' (vibe_intro), 'stuck_solver' (vibe_weave solve), 'held_half' (a Fable-held reply), 'fable'.",
      +  "type": "string"
      +}
    • addedInput schema / properties / payload
      Added value: +{
      +  "description": "Optional structured data (game state, code review, handoff, etc.)",
      +  "type": "object"
      +}
    • addedInput schema / properties / reply_to
      Added value: +{
      +  "description": "Optional: Message ID to reply to (creates a threaded reply)",
      +  "type": "string"
      +}
    • addedInput schema / properties / tip_amount_cents
      Added value: +{
      +  "description": "Optional: Attach an instant USDC tip (100 = $1, 500 = $5, 1000 = $10)",
      +  "type": "number"
      +}
    • changedInput schema / required
      Previous value: -[
      -  "handle",
      -  "message"
      -]New value: +[
      +  "handle"
      +]
  3. First observedv0.4.10

TDQS

A4.2/5.0
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 meaningful work: it discloses asynchronous delivery ('waits for their next turn — nobody has to be online') and the exact-text/no-context behavior. It doesn't cover every edge case like errors or permissions, but for a DM-sending tool it gives the agent the key 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?

Two sentences with no filler: the first names the action and the async behavior; the second clarifies an important constraint. It is front-loaded and every sentence earns its place.

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?

The schema is rich enough to cover parameter semantics, and the description covers the key behavioral context for sending a message. Since there are no annotations and no output schema, slightly more detail about send confirmation or error behavior could help, but the definition is complete enough for correct invocation.

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 documents every parameter in detail, including origin values, approved_sha256 formatting, and idempotency semantics. The description adds only a general note that the message is sent exactly as given, which is useful but not necessary to understand the parameters.

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: 'Send a direct message to someone on /vibe.' It goes beyond a simple restatement by explaining the delivery behavior and clarifying what the tool does not do ('doesn't attach repository or session context'), which distinguishes it clearly from the sibling vibe_* tools.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description makes the use case clear: use this when you need to DM someone on /vibe, and it works whether or not they are online. It does not explicitly name alternatives or say when not to use it, but the sibling set (status, inbox, help, capabilities, etc.) is distinct enough that an agent can infer the right tool.

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