Skip to main content
Glama

get_model_catalog

Get available Sequencer AI models for a given modality (image, video, audio, music). Call before choosing a generation model and follow the returned modelSelectionGuidance for the task use case. Also use for model availability and exact IDs. Common aliases include Nano Banana Pro, Nano Banana 2, Nano Banana 2 Lite, Gemini image, Imagen, Z Image, Z-Image Turbo, MiniMax H3, PrunaAI P-Video, Happy Horse, Google Omni, Flux, GPT Image, Seedream, Recraft, Bria, Runway, Luma, Sora, Kling, Hailuo, Seedance, PixVerse, ElevenLabs, Fish Audio, Suno, and Lyria.

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": {
      "modality": "<modality>"
    },
    "name": "get_model_catalog"
  }
}

Input Schema

NameRequiredDescriptionDefault
limitNo
fieldsNoSelect optional fields; ID, name and category are always retained.
offsetNo
compactNoReturn selection, pricing and supported input/settings fields. Set false for full descriptions.
modalityYes
modelIdsNoExact catalog IDs for known choices; avoids loading the full category.
capabilityNoExact supported feature, such as text_to_music or image_to_video.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed7 schema fields changed
    • addedInput schema / properties / capability
      Added value: +{
      +  "description": "Exact supported feature, such as text_to_music or image_to_video.",
      +  "maxLength": 100,
      +  "type": "string"
      +}
    • addedInput schema / properties / compact
      Added value: +{
      +  "default": true,
      +  "description": "Return selection, pricing and supported input/settings fields. Set false for full descriptions.",
      +  "type": "boolean"
      +}
    • addedInput schema / properties / fields
      Added value: +{
      +  "description": "Select optional fields; ID, name and category are always retained.",
      +  "items": {
      +    "enum": [
      +      "description",
      +      "features",
      +      "price",
      +      "unit",
      +      "resolutionPrices",
      +      "inputConstraints",
      +      "variantSelector",
      +      "pricingVariants",
      +      "settings"
      +    ],
      +    "type": "string"
      +  },
      +  "maxItems": 9,
      +  "minItems": 1,
      +  "type": "array"
      +}
    • addedInput schema / properties / limit
      Added value: +{
      +  "default": 30,
      +  "maximum": 100,
      +  "minimum": 1,
      +  "type": "integer"
      +}
    • removedInput schema / properties / modality / description
      Removed value: -"The modality to get models for"
    • addedInput schema / properties / modelIds
      Added value: +{
      +  "description": "Exact catalog IDs for known choices; avoids loading the full category.",
      +  "items": {
      +    "maxLength": 160,
      +    "minLength": 1,
      +    "type": "string"
      +  },
      +  "maxItems": 20,
      +  "minItems": 1,
      +  "type": "array"
      +}
    • addedInput schema / properties / offset
      Added value: +{
      +  "default": 0,
      +  "maximum": 500,
      +  "minimum": 0,
      +  "type": "integer"
      +}
  2. First observed

TDQS

A3.5/5.0
Behavior3/5

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

No annotations are provided, so the description carries the full behavioral burden. It discloses the workflow contract (query first, then obey modelSelectionGuidance) and the existence of a compact vs. full response only implicitly, but says nothing about pagination behavior, default result size, permission requirements, or whether the catalog is cached/live. Read-only intent is implied by 'Get' but never stated.

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

Conciseness3/5

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

The first two sentences are tightly front-loaded and earn their place. The third sentence is a raw dump of roughly thirty model aliases that consumes the majority of the text and will age badly; a single clause stating that common product aliases are resolvable would convey the same affordance.

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 no annotations and no output schema, a 7-parameter tool needs more from the description than it gets. It covers purpose, workflow position, and the returned guidance field, but leaves paging, projection (fields/compact), and ordering behavior unexplained, leaving an agent to discover the response shape by trial.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 57%, so roughly half the parameters are documented in the schema and half are not. The description adds real meaning for modelIds ('exact IDs') and for capability-style lookup via the alias list, but never mentions limit, offset, compact, or fields — the params most likely to be misused. Baseline 3 fits a partial-coverage schema with modest description compensation.

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?

States a specific verb and resource ('Get available Sequencer AI models') and narrows scope to a modality set (image, video, audio, music). It also signals secondary uses (availability, exact IDs), so an agent knows what it returns. It stops short of naming how it differs from adjacent catalog-style siblings such as get_sequencer_capabilities or get_feature_list.

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?

Explicit sequencing guidance: 'Call before choosing a generation model and follow the returned modelSelectionGuidance for the task use case.' That is a clear when-to-use with a defined follow-up action. It lacks any when-not-to-use or named alternative for cases where a different catalog tool is the right entry point.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.