Deep Thought Marketing

Submit a campaign to Deep Thought

submit_campaign

Turns the person's media plan into a campaign order for the Deep Thought team. Uses their latest plan from build_media_plan unless channels are given. Call first without confirmed to get a summary, show it, and call again with confirmed: true only after they say yes. A person on the Deep Thought team reviews every order before anything goes live (usually within 1 business day); nothing is charged or launched by this tool. Approved campaigns are billed monthly (month to month, cancel anytime); say so. If no card is on file, it returns a secure Stripe link to save one.

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": "submit_campaign"
  }
}

Input Schema

Name	Required	Description
`notes`	No	Anything else the team should know: offers, services to push, areas to avoid.
`website`	No	The business website, if they have one.
`channels`	No	Optional. Overrides the plan's channels. Each item: a channel id from list_channels and its monthly dollars.
`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.
`start_preference`	No	When they'd like to start, e.g. 'as soon as possible' or 'December 1'.

Schema Changelog

Changes observed during successful MCP inspections.

First observedNov 5, 2026

TDQS

A4.6/5.0

Behavior4/5

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

Goes well beyond the annotations by disclosing that a human reviews every order within about one business day, that nothing is charged or launched by the call, that approved campaigns bill monthly with cancel-anytime terms, and that a Stripe link is returned when no card is on file. The two-call confirmation pattern is consistent with idempotentHint=false. It could still say more about what happens to an unconfirmed call's state (whether a draft order is created), which keeps it from 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?

Front-loaded with purpose, then the confirmation protocol, then review timing, billing, and the Stripe fallback. Every sentence carries operational information the agent must relay or act on, though the density of separate obligations (say the billing terms, show the summary) makes it slightly long for a single read.

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?

With no output schema and no required parameters, the description still tells the agent what comes back: a summary to show the person, and a secure Stripe link when no card is on file. Combined with the human-review and billing disclosures, nothing an agent needs to invoke and explain this tool correctly 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 100%, so the baseline is 3, but the description adds real meaning: it explains that 'channels' overrides the plan's channels, and it elaborates the operational semantics of 'confirmed' as a two-phase preview-then-commit flag rather than a simple boolean. The notes, website, and start_preference parameters are left entirely to the schema.

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 concrete verb and resource: it turns the person's media plan into a campaign order for the Deep Thought team. It also distinguishes itself from the sibling build_media_plan by naming that tool as the default source of channels, so an agent can tell the two apart without opening either schema.

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?

Gives an explicit two-step protocol: call without confirmed to get a summary, show it, then call again with confirmed: true only after the person agrees. It also states the alternative source ('unless channels are given'), leaving nothing to inference about when to pass channels versus relying on the saved plan.

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?