Deep Thought Marketing

Request a campaign change

request_change

Asks the Deep Thought team to change a campaign: resume a paused campaign, change the budget, change channels, change the ads, or something else. Nothing changes until a person on the team approves it (usually within 1 business day). Call without confirmed first, show the summary, then call again with confirmed: true after they say yes.

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": {
      "order_id": "<order_id>",
      "type": "<type>",
      "details": "<details>"
    },
    "name": "request_change"
  }
}

Input Schema

Name	Required	Description
`type`	Yes
`details`	Yes	What they want changed, in their words, with numbers where given.
`order_id`	Yes	The campaign's order id, from my_campaigns.
`confirmed`	No	Set true only after the person has seen the summary and said yes. Leave out (or false) to get the summary to show them first.

Schema Changelog

Changes observed during successful MCP inspections.

First observedNov 5, 2026

TDQS

A4.6/5.0

Behavior5/5

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

Adds substantial context beyond the annotations: nothing is applied until a human approves, approval usually takes one business day, and the confirmed flag gates the actual submission. This is exactly the out-of-band behavior an agent needs and cannot infer from readOnlyHint=false / openWorldHint=true.

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 what the tool does, then the approval caveat, then the mechanics; every sentence carries information. The final sentence slightly overlaps the schema's confirmed description, but the repetition is justified for a safety-critical step.

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 four-parameter mutation with no output schema, the description covers what happens (nothing until approval), timing (one business day), and the required call sequence. Nothing an agent needs to invoke it safely is missing.

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 75%, so most parameters are documented structurally, but the description explains the intent of the confirmed workflow and the two-call pattern that the schema only states in shorthand. It adds meaningful operational meaning rather than restating field definitions.

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 ('Asks the Deep Thought team to change a campaign') and enumerates the concrete change types (resume, budget, channels, ads, other) that map to the type enum. This is clearly distinguishable from direct-action siblings like pause_ads or submit_campaign.

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 when-to-use guidance through the required two-step protocol: call without confirmed to get a summary, then call again with confirmed: true after the person approves. It stops short of naming which sibling to use for cases like immediately pausing ads (pause_ads) versus requesting a change, so the boundary against alternatives is only implied.

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

All Deep Thought Marketing 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?