Skip to main content
Glama

Reply To Conversation

reply_to_conversation
Destructive

Reply inside an existing Canvas Inbox conversation so every participant receives your message. Use it to answer a thread instead of starting a new one with send_message.

Instructions

Reply within an existing Canvas Inbox conversation. Every participant receives it. Use send_message to start a new thread. [NEEDS CONFIRMATION: call it once for a preview and a confirm_token, show the preview to the user, and only if they say yes call it again with the same arguments, confirm=true and that confirm_token. Apps that can ask the user directly show a confirmation instead.]

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": {
      "conversation_id": "<conversation_id>",
      "body": "<body>"
    },
    "name": "reply_to_conversation"
  }
}

Input Schema

NameRequiredDescriptionDefault
bodyYesMessage body text. Plain text or simple HTML.
confirmNoSet to true together with confirm_token to carry out a request you already previewed.
confirm_tokenNoThe one-time token from the preview. Only use it after the user has said yes.
conversation_idYesInbox conversation ID (numeric string). Get it from list_conversations.
included_message_idsNoOptional IDs of earlier messages in the thread to quote in this reply, from get_conversation.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changedv1.3.0
    • changedInput schema / properties / confirm / description
      Previous value: -"Must be true to actually execute. Omit or set false to get a dry-run preview first."New value: +"Set to true together with confirm_token to carry out a request you already previewed."
    • addedInput schema / properties / confirm_token
      Added value: +{
      +  "description": "The one-time token from the preview. Only use it after the user has said yes.",
      +  "type": "string"
      +}
  2. Changed3 schema fields changedv1.0.2
    • addedInput schema / properties / body / description
      Added value: +"Message body text. Plain text or simple HTML."
    • changedInput schema / properties / conversation_id / description
      Previous value: -"Canvas ID (numeric string)"New value: +"Inbox conversation ID (numeric string). Get it from list_conversations."
    • addedInput schema / properties / included_message_ids / description
      Added value: +"Optional IDs of earlier messages in the thread to quote in this reply, from get_conversation."
  3. First observedv1.0.1

TDQS

A4/5.0
Behavior4/5

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

Annotations already declare destructiveHint=true, idempotentHint=false and openWorldHint=true; the description adds real value beyond them by disclosing fan-out to every participant and the two-phase preview/confirm_token protocol that governs the actual send. The parenthetical is marred by an editorial '[NEEDS CONFIRMATION: ...]' marker and a somewhat confusing note about apps that can prompt the user directly, which blunts the otherwise strong disclosure.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness3/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The first two sentences and the send_message routing are tight and front-loaded, but the trailing bracketed confirmation block is one long parenthetical carrying an unresolved editorial placeholder, which reads as drafting notes rather than tool documentation.

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 5-parameter mutating tool with annotations present and no output schema, the description covers purpose, audience, alternative, and the confirmation protocol an agent must follow. It omits what the call returns (e.g. the created message reference) and any limits on body size or HTML handling, but nothing essential to invoking it correctly 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 body, conversation_id, confirm, confirm_token and included_message_ids are already documented in the schema. The description only restates the confirm flow at a high level and adds no syntax, format, or quoting semantics beyond what the schema fields say; baseline 3 applies.

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 and resource ('Reply within an existing Canvas Inbox conversation') and immediately clarifies the blast radius ('Every participant receives it'), which distinguishes it from a private or thread-starting action. It also names the sibling it is not ('Use send_message to start a new thread'), so an agent can disambiguate without opening either schema.

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?

Explicitly routes the agent to send_message when the goal is a new thread, which is the key alternative in this tool family. It does not address other plausible confusions (e.g. reply_to_entry for discussions vs. inbox conversations), but the primary when/when-not pair is clearly stated.

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