Skip to main content
Glama

List the options

get_options
Read-onlyIdempotent

Video types, Look categories, background sources, formats and the current credit prices Everything a request can choose from, with the credit table (plans and credit_packs: the plan catalog the app shows, each plan's monthly credits, limits, features and shelf, its prices in cents and the app's highlighted one, and each pack's credits and price; reference only, nothing is bought through the API; music_video.categories: each kind, with demos, the real music videos of it Kinetune chose: one per model (model: its id) and a fallback (model null) for a model without its own; each with sound in video_url, a few silent seconds from its poster moment hover_seconds in hover_url, its poster in still_url, made_with: the model and quality it was made with, and story: its brief, the director's idea and its shots; signed for about a week. Show the one for the model in hand, else the fallback; demo is the fallback alone, as before. music_video.styles: each visual style (how the video is rendered), with its one picture: image_url (512 px square WebP) and thumbnail_url (160 px); its demo and demos are deprecated (still given until 2027-05-05: use image_url). music_video.models[].guide: what each model is best for (best_for), its strengths and weaknesses, the kinds it suits, its sharpest resolution (max_quality), public benchmark scores (board, entry, score, source, url, date) and page_url, the page comparing them; music_video.categories[].recommended_model: the offered model to suggest for that kind when the person hasn't named one. The catalog is set by Kinetune's admins and can change; a subscription keeps what it was bought with. credits.character_sheet: what drawing one character sheet costs now (draw_character_sheet). credits.cover: what a round of covers costs now, counts by how many (1 to 4), and redraw, one cover redrawn with a note (make_cover, redraw_cover). credits.examples: what a lyric video of a song_seconds song costs now in one 9:16 format, by how its Look is made (saved_look, new_look, new_look_ai_video), and clips: the same for the parts of a song people post (seconds: 15, 30, 60). Use it to pick a category or source and to explain prices.

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_options"
  }
}

Input Schema

NameRequiredDescriptionDefault

No arguments

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

B3.4/5.0
Behavior4/5

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

Annotations already establish read-only, idempotent, closed-world behavior, so the description's job is to add context, and it does: 'reference only, nothing is bought through the API,' the catalog is admin-controlled and can change, subscriptions retain what they were bought with, and signed URLs last about a week. It also flags deprecated fields with an explicit sunset date (2027-05-05) and a migration target, which is genuinely useful behavioral detail.

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

Conciseness2/5

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

After a reasonable first clause, the description collapses into a single run-on sentence that dumps nested field paths (music_video.categories[].recommended_model, credits.examples.clips) separated by semicolons. It is oversized for a no-parameter catalog tool and not front-loaded: the actionable guidance ('Use it to pick a category...') is stranded at the very end.

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, the description must carry the return shape, and it does so thoroughly: credit table structure, category demos with fallback semantics, style images, model guides, and per-action credit costs. The main gap is that the overall envelope (top-level keys like video types, formats, background sources mentioned in the first line) is never actually explained, despite being promised up front.

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?

The tool takes zero parameters, so there is no parameter meaning to convey and the baseline of 4 applies. The description instead documents response fields, which is not its obligation but does no harm.

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

Purpose3/5

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

The opening clause names concrete resources (video types, look categories, background sources, formats, credit prices) and the closing sentence frames it as the catalog a request chooses from, so the gist is recoverable. However, the purpose statement is buried under a wall of nested field documentation, and nothing distinguishes it from siblings like list_looks or list_music_video_looks that also surface option data.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The final sentence gives implied usage: 'Use it to pick a category or source and to explain prices,' which tells the agent this is the lookup for valid values and pricing. It offers no when-not guidance, no mention of alternatives, and no prerequisites, leaving the agent to infer that it should call this before draw_character_sheet, make_cover, etc.

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