Skip to main content
Glama

sockdock_get_status

Read-only

Verify SockDock is running and connected to Slack; report workspace, active runs, arrived channels, Claude Code/Codex sign-in status, owner DM notices, and available updates.

Instructions

Shows whether SockDock is running and connected to Slack, which workspace it is in, the runs in progress (with ids you can pass to sockdock_stop_run), which channels' posts have reached SockDock since it last connected (a restart clears this list, so an empty list right after a restart means nothing), whether Claude Code and Codex are signed in (claude_signed_in / codex_signed_in: false means that agent's rules fail until the user signs in), the owner (the person who uses SockDock; new DM rules are limited to them) with whether notices also go to them by DM, and a newer SockDock release when one is out. DMs show up in the arrived list as dm. Use it first when the user asks whether SockDock works, or before stopping a run. If SockDock is not running, the tool says so: ask the user to open the SockDock app.

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": "sockdock_get_status"
  }
}

Input Schema

NameRequiredDescriptionDefault

No arguments

Output Schema

NameRequiredDescriptionDefault
ownerNothe person who uses SockDock (registered in the app); new DM rules are limited to them, and notices go to them by DM when dm_notices is true. Absent when nobody is registered
runningYes
connectedYes
workspaceNo
dm_noticesYeswhether notices also go to the owner by Slack DM
last_errorNo
codex_signed_inNowhether the Codex that codex rules run is signed in; left out when unknown or no rule runs Codex
claude_signed_inNowhether the Claude Code that agent rules run is signed in; left out when unknown or no rule runs Claude Code
update_availableNoa newer SockDock release, when one is out; the user updates it from the menu bar app (or with brew upgrade). Absent when SockDock is up to date or the check is off
posts_arrived_fromYeschannel IDs whose posts have reached SockDock since it connected

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.2.0

TDQS

A4.5/5.0
Behavior5/5

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

Well beyond the readOnlyHint/openWorldHint annotations, it discloses consequential state semantics: the arrived-channel list is cleared by a restart so an empty list right after a restart is meaningless, claude_signed_in/codex_signed_in=false means that agent's rules will fail, and new DM rules are limited to the owner. It also describes the failure path ('If SockDock is not running, the tool says so: ask the user to open the SockDock app'), which tells the agent how to recover rather than just that an error occurs.

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 sentence sprawls across a dozen comma- and parenthesis-separated clauses in a single run-on, which makes scanning harder than a short bulleted enumeration would be. Almost nothing is redundant, but the structure undermines the otherwise front-loaded opening.

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?

Although an output schema exists and return values need not be restated, the description covers everything an agent needs to act: what is reported, how to interpret empty or false values, which returned ids feed sockdock_stop_run, and the recovery step when the app is down. Nothing material is missing for a zero-parameter status tool.

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?

With zero parameters the baseline is 4, and the description does add cross-tool semantics by noting that runs are returned 'with ids you can pass to sockdock_stop_run' and that DMs appear in the arrived list as 'dm'. This is meaningful value beyond an empty schema, though the remaining returned fields are described rather than their downstream use.

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 opens with a concrete verb+resource ('Shows whether SockDock is running and connected to Slack') and then enumerates exactly what the status payload covers: workspace, in-progress runs, arrived channels, agent sign-in flags, owner, and update availability. An agent can distinguish this from all twelve siblings (list_runs, list_channels, list_rules, etc.) without opening a schema, because it is framed as the aggregate health snapshot rather than a per-entity list.

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?

It gives explicit triggers: 'Use it first when the user asks whether SockDock works, or before stopping a run,' which also routes the agent toward sockdock_stop_run for the follow-up action. There is no explicit when-not or named alternative to prefer for narrower queries, but the 'use it first' framing supplies clear context for invocation.

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