Skip to main content
Glama
Sign In
codex-intercom-mcp

codex-intercom-mcp

by ctliz
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Local

intercom_ask

Sends a question to another intercom session when your next step depends on its reply, with a timed wait and late-reply support. Use it for blocking clarifications, not status updates.

Instructions

Ask another intercom session a question only when the next step depends on its reply. Use intercom_send for assignments, progress/status checkpoints, and notifications.

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": {
      "to": "<to>",
      "message": "<message>"
    },
    "name": "intercom_ask"
  }
}

Input Schema

NameRequiredDescriptionDefault
toYes
teamNoTask team; required when multiple teams are shared.
messageYes
timeout_msNoSoft wait in milliseconds before continuing asynchronously (default 30000, max 120000); timed-out asks remain open for late replies.
attachmentsNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changedv0.14.0
    • changedInput schema / properties / timeout_ms / description
      Previous value: -"Maximum time to wait for a reply before returning an error. Use intercom_send plus intercom_pending for longer work."New value: +"Soft wait in milliseconds before continuing asynchronously (default 30000, max 120000); timed-out asks remain open for late replies."
  2. Changed1 schema field changedv0.13.0
    • addedInput schema / properties / team
      Added value: +{
+  "description": "Task team; required when multiple teams are shared.",
+  "type": "string"
+}
  3. First observedv0.11.0-connect.1

TDQS

A3.6/5.0
Behavior3/5

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

Annotations declare this is a mutating, non-idempotent, non-destructive, non-open-world call, so the safety profile is already supplied. The description adds the useful inference that the call blocks on a reply, but says nothing about the async timeout behavior, whether duplicate asks are deduplicated, or what a caller receives when no reply arrives – all of which matter for a non-idempotent tool.

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?

Two tight sentences with the eligibility condition front-loaded and zero filler. It is efficient, though the brevity edges into under-specification given the five parameters and the ask/reply lifecycle.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness2/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

There is no output schema, so the description is the only place an agent could learn what an ask returns (an answer inline, a pending handle, or nothing on timeout) – and it is silent. For a non-idempotent five-parameter tool with 40% schema coverage, this leaves real gaps around return shape, attachments, and addressing semantics for 'to'/'team'.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters2/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is only 40%, and the description contributes no parameter meaning whatsoever – 'to', 'message', and the entire 'attachments' structure (including its file/snippet/context enum) are undocumented in both places. With low coverage the description is expected to compensate, and it does not.

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 ('Ask another intercom session a question') and immediately bounds scope with 'only when the next step depends on its reply'. It also explicitly distinguishes itself from intercom_send, so an agent can pick between the two 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?

Gives an explicit gating condition (next step depends on the reply) and names the alternative tool plus the three categories of traffic that belong there. It stops short of covering the rest of the ask lifecycle – intercom_reply and intercom_pending, which are the obvious siblings for answering and draining open asks, are never mentioned.

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