Tevyon

Ask the Marketing Agent

ask_marketing_agent

Tevyon's Marketing Agent plans a small campaign: from the user's brief (product, goal, channels, audience, offer) it proposes up to four ready-to-post creatives, each a Marketing Agent style or template with its lettering or spoken line, format, length, a post caption and the credits of one run. It never starts a job. Show its reply (in the user's language) and the creatives with their credits; start a chosen one with run_marketing_style (style_id, wish, aspect, duration, the product photo, max_credits = credits). needs lists inputs still missing (product photo). Pass the product photo as photo so it plans for that product. It shares the Director's daily budget and models (list_director_models).

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": {
      "message": "<message>"
    },
    "name": "ask_marketing_agent"
  }
}

Input Schema

Name	Required	Description
`model`	No	A model id from list_director_models. Default: the free standard model.
`photo`	No	The product photo from create_upload or import_image (/api/media/uploads/…).
`history`	No	Earlier messages of this conversation with the agent, oldest first.
`message`	Yes	The brief in the user's words, e.g. «launch of my organic lemonade on Instagram, young urban audience».
`has_avatar`	No	True if the user has a photo of a person for UGC and people styles.
`product_name`	No
`product_description`	No

Schema Changelog

Changes observed during successful MCP inspections.

First observedNov 5, 2026

TDQS

A4.5/5.0

Behavior4/5

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

Beyond the annotations, the description discloses the output shape (reply plus up to four creatives with style, line, format, length, caption, credits), the explicit 'never starts a job' guarantee and the shared Director budget. It stops short of saying whether this planning call itself consumes credits or what budget exhaustion does, 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?

Purpose is front-loaded in the first sentence and the follow-up actions come last, so the structure is sound. The middle sentences are dense run-ons with heavy backticking, which costs a point but no sentence is filler.

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?

For a seven-parameter planning call with no output schema, it describes what comes back (reply, creatives, credits, `needs`) and how to act on it. Some ambiguity remains about credit consumption and error cases, but the essentials for correct invocation are present.

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 71%, so the schema already documents model, history and the product fields. The description adds real value by explaining that `photo` makes the agent plan for that specific product and by linking the returned credits to the sibling's `max_credits` argument — a cross-tool mapping the schema cannot express.

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 description names a specific verb and resource ('plans a small campaign', 'proposes up to four ready-to-post creatives') and immediately states the negative scope ('It never starts a job'), which separates it cleanly from run_marketing_style and ask_director. An agent can pick this tool without opening the 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?

It gives explicit when-to-use (user's brief with product, goal, channels, audience, offer), what to do with the result ('Show its reply ... start a chosen one with run_marketing_style'), and names the follow-up tool plus its arguments. Handling for incomplete input is covered via the `needs` list.

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

All Tevyon 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?