Skip to main content
Glama

Work IQ

ms_workiq
Destructive

Query the Microsoft Work IQ agent, call Work IQ tools by name, and read Graph paths with your own M365 permissions for directory and channel lookups.

Instructions

Reach the Microsoft Work IQ agent. Without parameters lists the tools Work IQ exposes; with question asks the agent directly; with entity_urls reads Graph paths using your own M365 permissions, which covers directory and channel lookups the other tools are refused. tool + arguments calls any Work IQ tool by name, including ones that create, update, delete or send. Not read-only.

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": "ms_workiq"
  }
}

Input Schema

NameRequiredDescriptionDefault
toolNoName of a Work IQ tool to call directly (see the no-parameter listing)
questionNoA question to put to the Work IQ agent
argumentsNoArguments for the named tool (requires tool)
entity_urlsNoGraph paths to read, e.g. ["/me/manager"] (1-10)

Schema Changelog

Changes observed during successful MCP inspections.

  1. Addedv1.1.0

TDQS

A4.1/5.0
Behavior4/5

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

Annotations already declare readOnlyHint=false, destructiveHint=true, openWorldHint=true and idempotentHint=false, and the description reinforces this rather than contradicting it by warning that tool+arguments can reach tools that create, update, delete or send, and that it is not read-only. It additionally discloses that entity_urls reads run under the caller's own M365 permissions, a detail not present in annotations. It does not describe failure modes or what the no-parameter listing returns, so not a 5.

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?

A single dense sentence with the primary purpose front-loaded and the four modes laid out in parallel; every clause carries information. The semicolon-chained phrasing is slightly harder to scan than a short bulleted mode list, but there is no filler.

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

Completeness4/5

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

For a tool with four modes, an open-ended passthrough (tool + arbitrary arguments), a nested object parameter and no output schema, the description covers all call shapes and the safety posture. Gaps remain on what the no-parameter listing looks like and how errors from a named Work IQ tool surface, but the essentials for correct invocation are present.

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%, so the schema already documents all four parameters, establishing a baseline of 3. The description adds the interaction semantics between them (that arguments requires tool, and that each parameter selects a different mode), but the schema itself already states 'Arguments for the named tool (requires tool)', so the incremental meaning is modest.

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 resource (the Microsoft Work IQ agent) and enumerates four distinct operating modes: no params lists tools, question asks the agent, entity_urls reads Graph paths, tool+arguments calls a named tool. It also contrasts itself with siblings by noting it covers directory/channel lookups the other tools refuse, so an agent can tell when this is the escape hatch.

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?

Explicitly maps each parameter combination to a mode, which is effectively when-to-use guidance for the four call shapes, and gives a selection reason versus siblings (lookups they are refused). It lacks an explicit when-not-to-use or a preferred-sibling recommendation for ordinary mail/calendar/chat work, which keeps it off a 5.

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