Skip to main content
Glama

graph_search_all

Search mail, calendar, files, and Teams in one relevance-ranked query to locate items when you do not know where they live.

Instructions

Search mail, calendar, files, and Teams in one relevance-ranked query.

Use this when you do not know where something lives. chatMessage cannot be combined with SharePoint entity types like site, list, listItem, drive, or driveItem, so search Teams messages separately.

Args: query: Search query string (KQL is supported). entity_types: Resource types to search (default ["message", "event", "driveItem"]). One or more of: message, event, driveItem, drive, site, list, listItem, chatMessage, person. size: Maximum number of hits to return (default 25, maximum 50). from: Number of hits to skip for paging (default 0). compact: Whether to flatten the response into one list of hits, each reduced to {id, rank, summary, resource_type, name_or_subject, web_url} (default false, which returns the full hitsContainers payload). id is the hitId, falling back to the resource id; name_or_subject is the resource subject, name, displayName or title; web_url is its webUrl or webLink; a field the hit does not carry is omitted.

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": {
      "query": "<query>"
    },
    "name": "graph_search_all"
  }
}

Input Schema

NameRequiredDescriptionDefault
fromNo
sizeNo
queryYes
compactNo
entity_typesNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.10.0

TDQS

A4.6/5.0
Behavior4/5

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

No annotations are provided, so the description carries the full burden and it does deliver: relevance-ranked ordering, a hard result cap of 50 despite the schema's enormous maximum, paging via `from`, and a concrete description of what `compact` returns versus the raw hitsContainers payload. What is missing is surrounding context such as authentication prerequisites or rate-limit behavior, which matters for a Graph-backed search.

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?

The usage rules are front-loaded before the Args block, and each argument is treated in one to three lines with no filler. The `compact` entry is dense but every clause describes a real behavior (fallback order for id, field omission rules), so the length is largely earned rather than padding.

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?

With no output schema, the description steps in to describe the return shape, at least for compact mode, and names the non-compact hitsContainers payload. Combined with explicit defaults, paging, and the cross-entity constraint, an agent has enough to call this correctly; only the unflattened response structure and auth prerequisites are left implicit.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters5/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0%, so the description must compensate and it does for all five parameters: KQL support for `query`, the full default and allowed entity type set, the real maximum of 50 for `size`, paging semantics for `from`, and the exact flattened field list produced by `compact`. The 50-cap and the compact output shape add genuine meaning the schema cannot convey.

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 opening sentence gives a specific verb (search), explicit resource scope (mail, calendar, files, Teams) and a ranking behavior (relevance-ranked) in one query. This naturally differentiates it from the single-source siblings such as graph_search_files and graph_search_mail, since it is the cross-source entry point.

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?

It states the selecting condition directly: 'Use this when you do not know where something lives.' It also gives an explicit exclusion/constraint: chatMessage cannot be combined with SharePoint entity types (site, list, listItem, drive, driveItem), so Teams messages must be searched separately. That is both a when-to-use and a when-not-to guidance in compact form.

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

Deploy Server

Other Tools