Skip to main content
Glama
Sign In

Tevyon

by ai.tevyon
OverviewDiscussionsAdmin

Run a preset

run_preset

Starts a preset on the user's photo and reserves its credits; they are refunded in full if the job fails or is blocked. The photo must be the user's own upload (create_upload or import_image). If people are shown in it, ask the user first whether everyone shown agreed to appear in the clip; pass consent true only then (it is always required). Pass max_credits (the credits from list_presets or ask_director) so the job only starts at the price you showed. idempotency_key is required: a new unique string per intended run, the same one only to retry it. Pass wait_seconds or poll get_job; clips take minutes.

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": {
      "preset_id": "<preset_id>",
      "image": "<image>",
      "consent": "<consent>",
      "idempotency_key": "<idempotency_key>"
    },
    "name": "run_preset"
  }
}

Input Schema

NameRequiredDescriptionDefault
wishNoA short extra wish in the user's words, e.g. «with a red cape». Required for a preset with line: the exact words spoken in the clip (up to 120 characters).
imageYesThe user's photo: the path from create_upload or import_image (/api/media/uploads/…).
consentYestrue only if the user confirmed that everyone shown in the photo agreed to appear in the clip (or nobody is shown).
preset_idYesFrom list_presets or a preset proposal of ask_director.
max_creditsNoThe credits from list_presets. The job does not start if it now costs more.
wait_secondsNoSeconds to wait for the job to finish (0 to 50).
idempotency_keyYesA new unique string per intended run, e.g. a UUID. Reuse it only to retry that run.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.8/5.0
Behavior5/5

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

Annotations only state it is not read-only, not destructive, and not idempotent; the description goes well beyond them by disclosing the credit reservation and full-refund policy on failure or blocking, the consent gate, the cost-ceiling behavior of max_credits, and the minutes-long latency. Those are exactly the side-effect and timing facts an agent needs before committing credits.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Dense and front-loaded: the action and credit consequence come first, then the photo/consent preconditions, then pricing and retry semantics, then latency. Every sentence carries a constraint the agent would otherwise get wrong; there is no 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 credit-spending mutation with no output schema, the description covers preconditions, safety consent, cost capping, retry semantics, and duration. The one gap is that it never states what is returned (presumably a job identifier), which matters because it tells the agent to poll get_job without saying what to poll with.

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 parameters are already documented, but the description adds workflow meaning the schema lacks: max_credits should be the figure shown to the user so the job only starts at that price, and idempotency_key must be new per run and reused only for retries. The consent and image-origin constraints are reinforced rather than new, which keeps it below a 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?

Opens with a precise verb and resource: 'Starts a preset on the user's photo and reserves its credits.' It also implicitly separates itself from list_presets (price lookup) and ask_director (preset proposal) by naming them as sources of preset_id/credits, so an agent can route without opening any 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 concrete when-to-use prerequisites: the photo must come from create_upload or import_image, and the agent must ask the user about consent before passing consent=true. It also prescribes the alternative to waiting ('Pass wait_seconds or poll get_job'), covering the main branching decision in the workflow.

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