Skip to main content
Glama

Post a proactive room update

post_room_update

Posts a durable, low-noise Chat room update when background work reaches an outcome or a blocker changes, using an idempotency key to prevent duplicate messages on retries.

Instructions

Posts one durable, low-noise update into a Chat room without waiting for another human turn. Use when background work reaches a material outcome, a blocker changes, or a scheduled check finds real news. Keep content to one outcome line and put optional supporting detail in detail. idempotency_key is required so retries never duplicate a message.

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": {
      "thread_id": "<thread_id>",
      "content": "<content>",
      "idempotency_key": "<idempotency_key>"
    },
    "name": "post_room_update"
  }
}

Input Schema

NameRequiredDescriptionDefault
kindNooutcome
detailNoOptional collapsed supporting detail.
contentYesOne-line outcome, maximum 320 characters.
sender_idNoStable seat handle shown as the author.
thread_idYesChat thread UUID receiving the update.
source_refNoOptional job, card, run, or commit reference.
idempotency_keyYesStable retry key for this exact update.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Addedv0.1.11

TDQS

A3.9/5.0
Behavior4/5

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

Annotations already declare non-read-only, non-destructive, non-open-world, and idempotentHint=false; the description adds genuinely new context by explaining that the required idempotency_key is what prevents duplicate messages on retry (i.e., dedupe is caller-driven, consistent with idempotentHint=false). It also discloses the "durable, low-noise" delivery character and the brevity constraint, though it says nothing about return value or failure behavior.

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?

Four short sentences, front-loaded with what the tool does before when-to-use and parameter rules; nothing is padded. The content/detail sentence largely repeats schema field descriptions, which costs a point.

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

Completeness3/5

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

For a mutating 7-parameter tool with no output schema, the description covers purpose, triggers, and the critical idempotency contract, but omits what the call returns (message id?) and what the four `kind` enum values mean—both of which the schema also leaves silent.

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

Parameters4/5

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

Schema coverage is 86%, so the baseline is 3; the description adds functional meaning beyond the schema by tying idempotency_key to retry-with-same-key behavior and by restating content/detail as one-line outcome vs. optional supporting detail. It leaves the `kind` enum (ack/outcome/card/checkin) and sender_id/source_ref unexplained.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

Names a specific verb and resource ("Posts ... update into a Chat room") and constrains it to proactive/background use "without waiting for another human turn," which distinguishes it from a reply-style post_message. It stops short of naming the sibling it replaces, so the contrast is inferred rather than stated.

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 concrete trigger conditions: background work reaches a material outcome, a blocker changes, or a scheduled check finds real news. It also implicitly excludes conversational replies. There is no explicit when-not or named alternative tool, which keeps it below 5.

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