Skip to main content
Glama

sockdock_find_users

Read-only

Finds Slack workspace members by partial display or real name and returns their member IDs (U…), so you can fill allowed_users in rules or look up a poster's ID for match testing.

Instructions

Finds people in the Slack workspace by part of their display name or real name and returns their member IDs (U…). Use it to fill allowed_users in sockdock_save_rule when the user names who may run a rule ("only Taro and me"), or to get a poster's ID for sockdock_test_match. Several people can share a name: if more than one matches, ask the user which one. It needs the users:read scope on the Slack app; problem missing_scope means it is missing: ask the user for member IDs (Slack profile → Copy member ID), or to add users:read to the Slack app and reinstall it.

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": {
      "name": "<name>"
    },
    "name": "sockdock_find_users"
  }
}

Input Schema

NameRequiredDescriptionDefault
nameYespart of a display name or real name (case-insensitive), or a member ID

Output Schema

NameRequiredDescriptionDefault
peopleYes
problemNowhy people cannot be listed: missing_scope (the Slack app lacks users:read; ask the user for member IDs, or to add users:read and reinstall the app), unavailable (not connected) or error

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.2.0

TDQS

A4.6/5.0
Behavior5/5

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

Beyond readOnlyHint/openWorldHint, it discloses the Slack auth dependency (users:read scope), the exact error code (missing_scope), and two concrete remediations — ask for a copied member ID or reinstall the app with the scope. It also warns that names are non-unique, which is real behavioral context an agent cannot get from annotations.

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?

Purpose is front-loaded in the first sentence and each following sentence adds a distinct fact (routing, ambiguity, auth, remediation). The final remediation sentence is dense with two alternatives but nothing is filler; a short bulleted structure would read marginally better.

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 one-parameter lookup with an output schema, the description covers everything the agent needs: what it does, when to call it, how to resolve multi-match ambiguity, and how to recover from the only realistic failure (missing scope). Return values need not be explained since the output schema 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% and the single parameter is already documented as case-insensitive partial name or member ID, so the description mostly restates it. It does add the useful behavioral note that several people can share a name, which is about result ambiguity rather than the parameter itself, so the baseline 3 holds.

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 ('Finds people in the Slack workspace by part of their display name or real name') and even names the return shape (member IDs starting with U…). This is immediately distinguishable from the rule-management siblings, which never look up people.

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?

Explicitly routes the agent: use it to fill allowed_users in sockdock_save_rule when a user names who may run a rule, or to get a poster's ID for sockdock_test_match. It also gives a decision rule for the ambiguous case ('if more than one matches, ask the user which one'), leaving nothing to inference.

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