Skip to main content
Glama

Kubeez

get_models

Read-onlyIdempotent

Scope: none (any authenticated key). List available AI models with costs, limits, and input requirements. Call it when you are unsure a model or capability exists, or when comparing models — use only model_id values returned here. NARROW THE LIST, do not read all of it: the unfiltered video catalog is over 140 rows. accepts='image'|'video'|'audio'|'document' keeps only models that take that input type. duration_s= keeps only models that can render that clip length. sort='price' orders cheapest-first at that duration (default 'id'). verbose=false drops usage_notes / cost_note / estimated_time_seconds for a compact pick list. Example, animating a logo into an 8-second clip: get_models(model_type='video', accepts='image', duration_s=8, sort='price', verbose=false). PRICE: compare models on price_for, never on cost_per_generation. price_for maps duration in seconds to the COMPLETE credit cost at that length (e.g. {'8': 45} = 45 credits for an 8-second render), so price_for['8'] is directly comparable across every model, and its ABSENCE means the model cannot do 8 seconds. billing_unit ('per_second' | 'per_generation' | 'per_1000_chars' | 'per_minute') and rate give the underlying unit. cost_per_generation is legacy and NOT unit-comparable — for per-second models it is a pre-multiplied example duration that differs per family. Each model also returns: model_id, duration_range_s, estimated_time_seconds (REAL — DB-authored override or historical average of past completions; use it as the first-poll delay, do NOT poll every second), requires_input_media, input_media_types (e.g. ['image'] or ['image','video']), generation_types, capabilities (prompt_max_chars, duration_options, max_input_images, max_input_videos, supports_negative_prompt, supports_sound, video_audio), and usage_notes with exact rules. For video models, video_audio is critical: 'included' = audio in output without sound param; 'toggle_via_sound_param' = sound true/false controls audio and DEFAULTS ON, so audio is on for every supporting model unless you explicitly silence it (free on Seedance 2; Kling 2.6 and Kling 3.0 charge extra for audio but still default on, so state the higher price in your quote); 'always_on_flat_rate' = audio is always produced and the price does not change with it; 'silent' = no generated audio (Seedance 1.0). Only pass sound=false when the user explicitly asks for a silent clip. Do not answer 'which models have audio' using only supports_sound — that flag only means the sound parameter exists for toggling. latest_in_family maps a family to the CHEAPEST variant of its newest release. When requires_input_media is true, you MUST pass source_media_urls with the correct count and types to generate_media. If the user has media only on their device (no URL), use get_upload_url → user uploads at link → get_upload_session before generate_media — see those tool descriptions.

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": "get_models"
  }
}

Input Schema

NameRequiredDescriptionDefault
sortNoid
acceptsNo
verboseNo
duration_sNo
model_typeNo

Output Schema

NameRequiredDescriptionDefault

No arguments

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.7/5.0
Behavior5/5

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

Annotations already declare readOnly/idempotent/non-destructive, so the description rightly spends its words on non-obvious behavior: the ~140-row catalog size, that unfiltered reads are wasteful, that price_for presence/absence encodes capability, and that estimated_time_seconds is real timing data to be used as a first-poll delay rather than a polling interval. The video_audio taxonomy and the warning not to infer audio from supports_sound are behavioral facts absent from any structured field.

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?

Scope, purpose, and the narrowing rule are front-loaded, which is correct, but the body becomes a dense wall of mixed concerns — parameter docs, return-field interpretation, pricing rules, and audio-semantics rules in one block. Most sentences are load-bearing, yet the price_for/cost_per_generation material is restated in several forms and would read better as separated clauses.

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?

For a zero-required-param listing tool with an output schema, this is more than complete: it supplies the interpretation rules an output schema cannot express (price_for vs legacy cost_per_generation, video_audio defaults and pricing consequences, latest_in_family meaning). Nothing needed to call it correctly — including the counts and types required for downstream generate_media calls — is 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 0%, so the description must carry parameter meaning, and it does: accepts values, duration_s semantics, sort='price' meaning "cheapest-first at that duration" with default 'id', and verbose=false dropping specific fields. model_type is only conveyed implicitly via the worked example rather than enumerated like accepts, which is the one small gap against a fully documented parameter set.

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 verb and resource up front ("List available AI models with costs, limits, and input requirements") and immediately adds scope ("Scope: none (any authenticated key)"). An agent can tell this apart from generation siblings like generate_media or estimate because the description frames it as the catalog/picker step.

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 when-to-use ("when you are unsure a model or capability exists, or when comparing models") and a hard constraint ("use only model_id values returned here"). It also gives a workflow branch for the media case (get_upload_url → user uploads → get_upload_session → generate_media), which tells the agent what to do instead when this tool isn't sufficient.

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.

Resources