AdCopilot

AdCopilot: workspace overview

get_org_context

Read-onlyIdempotent

Reads this workspace's AdCopilot context, for a get-started request or before working on the user's Google Ads. It only reads: it changes nothing in Google and nothing in the workspace's saved context. Returns which Google products are connected, the enabled Google Ads accounts (name, currency, time zone), whether campaigns and conversion tracking exist, the saved business profile, the onboarding stage, and a situation code with a suggested next_step, a playbook, and cross_reads: suggested reads in the workspace's other connected Google products (Analytics, Search Console, Tag Manager), with their arguments. Also returns tools_revision, the revision this connection's tool descriptions end with. Given tools, it repeats the current descriptions and input schemas of tools this connection already has, and runs none of them.

Tools revision: d80f65c0.

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": "get_org_context"
  }
}

Input Schema

Name	Required	Description
`tools`	No	Tool names (at most 10) whose current description and input schema to return instead of the context.
`refresh`	No
`customer_id`	No	A Google Ads customer id. The `profile` returned is that account's business profile; without it, the only switched-on account's, or the workspace's own.

Output Schema

Name	Required	Description	Default
`result`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

Changed2 schema fields changedNov 1, 2026

removedInput schema / properties / source

Removed value: -{
-  "anyOf": [
-    {
-      "type": "string"
-    },
-    {
-      "type": "null"
-    }
-  ],
-  "default": null,
-  "description": "\"claude-plugin\" when AdCopilot's Claude plugin is in this conversation (its skills or commands, such as /setup, are available); \"claude-scheduled\" when a Claude scheduled task or Claude Code routine is running. Any other value is ignored.",
-  "title": "Source"
-}

removedInput schema / properties / task

Removed value: -{
-  "anyOf": [
-    {
-      "type": "string"
-    },
-    {
-      "type": "null"
-    }
-  ],
-  "default": null,
-  "description": "With source \"claude-scheduled\": the scheduled task's opening words, up to the first comma. AdCopilot's own morning check opens \"AdCopilot morning check\" (or \"AdCopilot morning website check\"). Ignored without that source.",
-  "title": "Task"
-}

Changed1 schema field changedOct 25, 2026

addedInput schema / properties / customer_id

Added value: +{
+  "anyOf": [
+    {
+      "type": "string"
+    },
+    {
+      "type": "null"
+    }
+  ],
+  "default": null,
+  "description": "A Google Ads customer id. The `profile` returned is that account's business profile; without it, the only switched-on account's, or the workspace's own.",
+  "title": "Customer Id"
+}

First observedOct 23, 2026

TDQS

A4.6/5.0

Behavior5/5

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

Annotations already declare readOnly, idempotent and non-destructive, yet the description adds real behavioral context: nothing in Google and nothing in saved context is modified, and crucially the `tools` argument only echoes descriptions/schemas and 'runs none of them.' That non-obvious side-effect-free behavior is exactly what an agent needs and 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?

Front-loaded with the verb and safety statement, then a dense enumeration of return fields; nearly every clause carries information. It is long, and the trailing 'Tools revision: d80f65c0.' is static metadata that does not help tool selection.

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 zero-required-parameter overview tool with an output schema and full annotation coverage, the description covers scope, side effects, all returned sections, and the special `tools` mode. An agent can decide to call it and predict the response without opening anything else.

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?

Schema coverage is 67% and the schema already documents `tools` and `customer_id`. The description still adds meaning beyond the schema by clarifying that `tools` returns existing descriptions and schemas and executes nothing, and by framing `tools_revision` as the revision the connection's descriptions end with. The `refresh` parameter is never mentioned.

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 ('Reads this workspace's AdCopilot context') and then enumerates the payload: connected Google products, enabled Ads accounts, business profile, onboarding stage, situation/next_step/playbook. That is far more than a restatement of the name and lets an agent distinguish it from save_org_context and the many account-level read tools.

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?

Gives explicit trigger conditions: 'for a get-started request or before working on the user's Google Ads.' It does not name the counterpart write tool (save_org_context) as the alternative, so the when-not guidance is implied by 'it changes nothing' rather than stated.

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

All AdCopilot tools Inspect

Try in Browser

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources

Need Help?