Creatify Ad Agent

composer_voice_line

Speaks one or more lines using exactly one provider voice_id or authorized like samples. No voice design. Several lines write out_1.wav, out_2.wav, ...; a single line writes out. Each line is checked against its text by transcription; a failed task lists the lines that missed. Returns task_id and credit cost.

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": {
      "project_id": "<project_id>",
      "text": "<text>",
      "out": "<out>"
    },
    "name": "composer_voice_line"
  }
}

Input Schema

Name	Required	Description
`out`	Yes	Path relative to the project, e.g. gen/shot1.mp4.
`say`	No	Pronunciations for names and brands, each "WORD=SPOKEN" (e.g. "Vrbo=Ver-bo"). The voice reads SPOKEN; captions and the voice check keep WORD. Write amounts as digits in text instead.
`lead`	No	Seconds of silence before the line.
`like`	No	Clean samples to clone: a character generated in this project, the user's own voice, or a voice they have the rights to use.
`seed`	No	Random seed. An identical request (same seed) within 10 minutes returns the existing task.
`text`	Yes	The lines to speak, one clip per line.
`describe`	No	Removed; always rejected before charging. Use voice_id from composer_list_voices or authorized like samples.
`voice_id`	No	Provider voice_id from composer_list_voices, not a record UUID. Use exactly one of voice_id or like.
`project_id`	Yes	project_id from composer_project_create.

Schema Changelog

Changes observed during successful MCP inspections.

Changed1 schema field changedNov 3, 2026

addedInput schema / properties / say

Added value: +{
+  "anyOf": [
+    {
+      "items": {
+        "type": "string"
+      },
+      "type": "array"
+    },
+    {
+      "type": "null"
+    }
+  ],
+  "default": null,
+  "description": "Pronunciations for names and brands, each \"WORD=SPOKEN\" (e.g. \"Vrbo=Ver-bo\"). The voice reads SPOKEN; captions and the voice check keep WORD. Write amounts as digits in text instead.",
+  "title": "Say"
+}

First observedOct 19, 2026

TDQS

A4/5.0

Behavior4/5

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

Annotations only declare write + openWorld + non-destructive; the description adds substantive behavior: per-line output file naming (out_1.wav, out_2.wav vs. out), a transcription-based verification pass, a failure mode that lists missed lines, and a returned task_id with credit cost. The one notable omission is that it doesn't tell the agent the call is asynchronous and should be polled via composer_task_status.

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?

Four short sentences, each carrying distinct information, front-loaded with the core action and voice-source constraint. No filler or restatement of the tool name.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With 9 parameters, no output schema, and a task-based return, the description covers outputs, cost, and verification adequately, but it never states the async lifecycle (poll composer_task_status) or what the returned task_id is used for. That is the main gap an agent would hit at invocation time.

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 meaning the schema does not: how the `out` path fans out into numbered files for multiple lines, and that 'describe' is unconditionally rejected. That is genuine clarification beyond the field descriptions.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

"Speaks one or more lines using exactly one provider voice_id or authorized like samples" gives a concrete verb (speak/render audio), resource (voice lines), and scope (one voice source per call). The clause 'No voice design' additionally excludes a neighboring capability, though no sibling tool is named by name (e.g. composer_generate_music or composer_generate_clip).

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?

It routes the agent to composer_list_voices for the voice_id and states the mutual exclusivity of voice_id vs. like, plus that 'describe' is rejected before charging. It does not say when to prefer this over composer_generate_clip or composer_generate_music, so the when-not guidance is incomplete rather than absent.

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

All Creatify Ad Agent 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?