Skip to main content
Glama
Sign In

Creator MCP

by com.lottiefiles
OverviewDiscussionsAdmin

Creator API writing docs

creator_docs
Read-onlyIdempotent

Creator API reference. lookup: signature, units, example and related calls for each named method or enum member (all names in one call, e.g. ["setParentInPlace", "PropertyType.Scale"]). query: plain-words search ("fade a shape"). topic: a page (overview, shapes, animation, paints, effects, masks, render, slides, video, edit, import) or section of guide, patterns, api (guide/units, api/paints), up to four comma-separated. About 100 tokens a lookup name, a page a few hundred to 1,500.

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": "creator_docs"
  }
}

Input Schema

NameRequiredDescriptionDefault
queryNoFree-text search over names, parameters and doc text, e.g. "fade a shape" or "export video". Returns the top 5 matches, any matching how-to answer, and the sections worth reading next.
topicNoA page (see the tool description), or a section such as guide/units or api/paints; up to 4 comma-separated. Common synonyms (export, colors, deck, mp4, ...) resolve too.
lookupNoEvery method or enum-member name you are about to use, in one call, e.g. ["setParentInPlace", "PropertyType.Scale"]. An invented name that has a real equivalent resolves to it; about 100 tokens per name.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.3/5.0
Behavior4/5

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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, closed-world), so the description correctly focuses on behavior it can add: response shapes per mode and explicit token costs ('about 100 tokens a lookup name, a page a few hundred to 1,500'). This cost disclosure is genuinely useful planning information that annotations cannot convey; only rate limits or whether modes can be combined are unaddressed.

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 reference line and the three mode names are front-loaded in a single dense paragraph, and every clause carries operational detail (examples, page lists, token budgets). The heavy use of backticks and parentheticals makes it slightly cramped to parse but there is little wasted wording.

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?

With no output schema present, the description does the work of explaining returns: signature/units/examples for lookup, top-5 matches plus a how-to answer and follow-up sections for query, and sized pages for topic. It is nearly complete for a docs tool; the only real gap is whether parameters can be mixed in one call.

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 enumerates the valid `topic` pages (schema defers to the description for these values), restates the batch semantics of `lookup` ('all names in one call'), and attaches per-name token cost to `lookup`. It does not clarify whether the three parameters can be supplied simultaneously.

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 opens with a specific resource ('Creator API reference') and then enumerates three distinct modes (`lookup`, `query`, `topic`) with a concrete example for each. An agent can immediately tell this is a documentation-retrieval tool, distinct from the mutation/file-oriented siblings like creator_delete_file or creator_exec.

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 gives clear mode-selection guidance: `lookup` for names 'you are about to use', `query` for plain-words search like 'fade a shape', and `topic` for whole pages. It does not state exclusions or when not to use it, and mode-combination rules are only hinted at ('up to four comma-separated' for topic), so it falls short of a full when/when-not treatment.

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

All Creator MCP 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