Skip to main content
Glama
Office MCP Server

Office MCP Server

by hvkshetry

procurement_read

Read structured Microsoft 365 source inventories and changes with preserved pagination, without sending mail or modifying files. Reuse the same source IDs with each cursor.

Instructions

Read structured Microsoft 365 source inventories and changes, preserving pagination. Does not send mail or modify files. Pass the same source IDs with each nextLink/deltaLink cursor.

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": {
      "operation": "<operation>"
    },
    "name": "procurement_read"
  }
}

Input Schema

NameRequiredDescriptionDefault
cursorNo
item_idNo
mailboxNo
site_idNo
drive_idNo
folder_idNo
operationYes
message_idNo
version_idNo
attachment_idNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv1.0.0

TDQS

C2.9/5.0
Behavior3/5

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

No annotations exist, so the description must carry the burden, and it does contribute real behavior: it declares itself read-only in effect, warns that pagination state must be preserved, and gives the critical constraint that source IDs must be repeated on every nextLink/deltaLink call. It still omits what a cursor returns, whether delta cursors expire, permission requirements, and result shape for thirteen different operations.

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?

Three short sentences, front-loaded with the read-only scope and ending on the cursor mechanic; nothing is padded. The only cost is that brevity is achieved partly by omitting the operation surface entirely.

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

Completeness2/5

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

For a ten-parameter tool with a thirteen-value required enum and no output schema or annotations, the description leaves the central selector undocumented. An agent can read the intent but cannot determine which IDs pair with which `operation` value without reverse-engineering the schema.

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?

Expected 2 given the evidence.

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

Purpose3/5

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

The verb 'read' and the resource 'Microsoft 365 source inventories and changes' are stated, but 'source inventories' is abstract and the description never mentions the dominant `operation` parameter or the thirteen distinct resources (sites, users, drives, mail_delta, attachments, versions, file_content) it actually reaches. An agent learns it is a read surface, but not which of many possible reads this tool performs.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines2/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The only routing signal is the negative 'Does not send mail or modify files', which nudges away from write use but names no sibling alternative or positive when-to-use condition. The cursor sentence is a calling instruction rather than guidance about when this tool is the right choice over files, mail, or search.

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