Skip to main content
Glama
Sign In

Tevyon

by ai.tevyon
OverviewDiscussionsAdmin

Ask the Director

ask_director

Tevyon's Director is a creative planner: it turns the user's wish into 2–3 concrete, priced proposals, either a custom generation (model, title, the hook of its first second, prompt and settings) or a one-click preset; the first one (recommended) fits best. It never starts a job. Show its reply (written for the user, in the user's language) and the proposals with their credits. Start a custom proposal with generate (its job_type and params, max_credits = credits) only after the user chose it. A proposal with uses_photo starts on the user's photo: before you start it, ask the user to confirm they have the consent of everyone shown. Proposals with start "run_preset" are presets: start them with run_preset (the user's photo and their consent needed). suggestions (if any) are short replies the user might send next: offer them, never send one on your own. Continue a conversation by passing the earlier messages as history. The default model plans for free within a daily budget; the strongest models (list_director_models) cost credits per message, so never retry a call on your own.

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_director"
  }
}

Input Schema

NameRequiredDescriptionDefault
modelNoA model id from list_director_models. Default: the free standard model.
photoNoPath of the user's photo from create_upload or import_image (/api/media/uploads/…), for proposals built on it.
historyNoEarlier messages of this conversation with the Director, oldest first (its replies as assistant).
messageYesThe user's wish in their own words, e.g. «a viral clip of my dog as a superhero, for TikTok».

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.6/5.0
Behavior4/5

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

Beyond the annotations, it discloses cost behavior (free default model within a daily budget, stronger models in list_director_models cost credits per message), a consent prerequisite for proposals with uses_photo, and the fact that it never launches a job. It stops short of describing latency, what a credits-exhausted failure looks like, or the reply shape in detail, so it is strong but not exhaustive.

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 purpose and the 'never starts a job' constraint are front-loaded, then the downstream steps follow in workflow order. It is dense and long, with a few clauses (e.g. the hook-of-first-second parenthetical) that could be trimmed, but almost every sentence carries operational guidance.

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, the description takes on the job of explaining what comes back (a reply written for the user in their language, proposals with credits, optional suggestions) and how to act on each variant. Nothing an agent needs in order to call it and follow up correctly appears to be 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: history continues a conversation by passing earlier messages, model choice drives cost, and photo can seed proposals that touch the user's image (with a consent check). It does not add syntax detail beyond the schema, so it does not reach 5.

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 actor and output: the Director turns a wish into 2-3 concrete priced proposals, either a custom generation (model, title, hook, prompt, settings) or a one-click preset. It also pins down the boundary ('never starts a job'), which cleanly separates it from generate and run_preset.

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 explicit routing rules: start a custom proposal with generate (its job_type and params, max_credits = credits) only after the user chose it; presets start with run_preset; suggestions must be offered, never sent autonomously; never retry a paid model call. When-to-use and when-not-to-act are both spelled out.

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

All Tevyon toolsInspect
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