Skip to main content
Glama
Sign In

Connections

by icu.connections
OverviewDiscussionsAdmin

Reply in a conversation

connections_message_reply
Destructive

Send a reply, as the member, into one of their own Connections conversations, to the other person or people in it. It cannot be unsent, so send only the text the member asked for. Needs the conversation id (from the inbox, starting with c:) and the text. It cannot start a conversation (use start_conversation), and refuses one the member is not in or that is blocked or closed.

Input Schema

NameRequiredDescriptionDefault
bodyYesThe reply text, exactly as it should be sent.
personNoLinked person to run this call as (first name). Omit to run as the connection's holder.
dry_runNoPreview only.
projectNoWorkspace to run this call in (id or name).
conversationYesThe conversation id as the inbox lists it (it starts with c:).

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • changedInput schema / properties / dry_run / description
      Previous value: -"Preview only; nothing is written."New value: +"Preview only."
  2. Changed2 schema fields changed
    • changedInput schema / properties / dry_run / description
      Previous value: -"Preview only: return what this call would do, with nothing written."New value: +"Preview only; nothing is written."
    • addedInput schema / properties / person
      Added value: +{
+  "description": "Linked person to run this call as (first name). Omit to run as the connection's holder.",
+  "type": "string"
+}
  3. Changed1 schema field changed
    • addedInput schema / properties / project
      Added value: +{
+  "description": "Workspace to run this call in (id or name).",
+  "type": "string"
+}
  4. Added

TDQS

A4.4/5.0
Behavior4/5

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

Annotations declare destructiveHint=true and openWorldHint=true; the description corroborates and adds practical context beyond them — irreversibility ("cannot be unsent"), a caution to send only the member's exact text, and server-side refusal conditions for blocked/closed/foreign conversations. It does not clarify whether the reply is attributed to the member or to the optional person, nor what a refusal looks like, so it stops short of 5.

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?

Four short sentences, front-loaded with what the tool does and what it requires, followed by the irreversible-write caution and the exclusion. No sentence is filler; each adds a distinct constraint.

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 destructive, no-output-schema write tool the core needs are covered: recipient scope, required inputs, irreversibility, and refusal cases. The one notable omission is dry_run — a preview path is especially valuable for an irreversible send, and the description never hints it exists.

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 conversation, body, person, project and dry_run are already documented in the schema. The description repeats the conversation-id format ("starting with c:") and the body requirement but adds no meaning for person, project, or dry_run. Baseline 3 is appropriate when the schema carries the load.

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 uses a specific verb and resource ("Send a reply ... into one of their own Connections conversations") and pins the scope to conversations the member already belongs to. It is immediately separable from connections_message_start, which it explicitly names as the alternative for starting a conversation.

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 states the when-not case ("It cannot start a conversation (use start_conversation)") and names the fallback, plus the refusal conditions: conversations the member is not in, or that are blocked or closed. That is explicit alternative routing rather than implied usage. Minor weakness: the referenced sibling is listed as connections_message_start, so the agent may need to map the shorthand.

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

All Connections toolsInspect
Try in Browser
One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources