Keeploop

Create Slack monitor

create_slack_monitor

Watch Slack conversations Keeploop's Slack app can read (list_slack_channels says which). Narrow by channel, thread (replies to one thread), dm, from_contains, text_contains or mentions_me; give at least one. The user's own messages are skipped unless include_own is true. Stops after ttl_hours or max_hits matches. Returns a token for check_monitor and cancel_monitor. It only records and notifies; it never sends, changes or deletes anything. routes tags the monitor for check_route; use 'duet:' for a Claude Duet channel so any later session there can read it. Requires Keeploop Pro.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "create_slack_monitor"
  }
}

Input Schema

Name	Required	Description
`dm`	No	Direct messages only.
`name`	No	A short name for the monitor.
`routes`	No	Up to 8 labels check_route reads this monitor's matches by, e.g. 'duet:fissler'. Lowercase letters, digits, '.', '_', ':' and '-'. A new monitor with routes has no Mac banner or ntfy push.
`thread`	No	Replies to one thread: a permalink or 'C0123:1727000000.123456'.
`channel`	No	A Slack channel name or id.
`max_hits`	No	Stop after this many matches; 1 for a one-shot watch.
`match_all`	No	Every direct message and mention of the user (needs routes).
`ttl_hours`	No	Stop after this many hours (default 24; no upper limit). 0 means no end: use it only when the user asks for a monitor that keeps running.
`include_own`	No	Also match what the user sent or wrote.
`mentions_me`	No	Only messages that mention the user.
`from_contains`	No	Sender address, number or name contains this.
`text_contains`	No	Message text contains this.

Output Schema

Name	Required	Description	Default
`note`	No
`monitor`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

AddedNov 2, 2026

TDQS

A4.6/5.0

Behavior5/5

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

Annotations declare destructiveHint=false but the description goes further, asserting "It only records and notifies; it never sends, changes or deletes anything" — reconciling the non-readOnly write with a no-side-effect promise. It also discloses lifecycle behavior beyond annotations: stops after ttl_hours or max_hits, own messages skipped unless include_own, returns a token, and that routed monitors get no Mac banner or ntfy push.

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?

Dense but well ordered: what it watches, how to narrow, filtering defaults, termination, return value, safety, then routing and plan gating. The opening sentence carries a long parenthetical aside that slightly interrupts front-loading, but nearly every clause earns its place.

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

Completeness5/5

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

For a 12-parameter creation tool with an output schema already covering returns, the description supplies everything an agent needs: filter requirement, defaults behavior, termination semantics, token handoff, plan gating, and explicit non-destructiveness. Nothing material is missing.

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 100%, so baseline is 3, but the description adds constraints the schema cannot express: at least one filter is required despite zero required parameters, ttl_hours=0 means no end and should only be used on explicit request, and the 'duet:' route prefix convention. Minor residual gaps (e.g., precedence among filters) keep it from a 5.

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 ("Watch Slack conversations") plus scope ("Keeploop's Slack app can read"), which separates it from the email/call/message monitor siblings. It also names the downstream tools it feeds (check_monitor, cancel_monitor) and points to list_slack_channels for discovery.

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 selection criteria — narrow by channel, thread, dm, from_contains, text_contains or mentions_me, and "give at least one" — plus routing guidance ("routes tags the monitor for check_route; use 'duet:<channel>'..."). The stated Pro requirement is an actionable prerequisite. It stops short of explicitly contrasting with the other create_*_monitor siblings, so not a 5.

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

All Keeploop tools Inspect

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.