Skip to main content
Glama

Singing Pet

Write a song for a pet

create_pet_song

Write and record a custom song about a pet from one photo, then make a short preview of the pet singing it. Use it when someone wants a personalised song or singing video of their own pet, for themselves or as a gift (birthday, Christmas, Mother's Day, gotcha day...). Needs a photo (image_url, or the attached photo), the pet's name, species and the occasion; ask for anything missing rather than inventing it. The preview (the whole song plus a 5 second singing clip) is free and takes one to two minutes; the HD video of the pet singing the whole song is bought at the checkout link that appears once the preview is ready. Returns at once with the song id and status previewing.

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": {
      "pet_name": "<pet_name>",
      "species": "<species>",
      "occasion": "<occasion>"
    },
    "name": "create_pet_song"
  }
}

Input Schema

NameRequiredDescriptionDefault
tierNostandard (768p) or deluxe (1080p). Only changes the paid HD video and its price or credit cost.
photoNoA photo the person attached in the chat. ChatGPT fills this in; other clients send image_url.
styleNoMusical style. Defaults to pop.
voiceNoThe singing voice. Defaults to female.
detailsNoQuirks, nicknames, favourite toys or habits, up to 300 characters. They make the lyrics personal.
paymentNocheckout (default): the preview is free and the person buys the HD video at a checkout link. credits: spend this account's API credits (100 for a standard song, 200 for deluxe) and render the HD video straight after the preview with no checkout. Only for developers who have bought credits; refused otherwise.
speciesYesWhat the pet is: dog, cat, rabbit, parrot...
languageNoLanguage the song is sung in. Defaults to the conversation's language, else English.
occasionYesWhat the song is for.
pet_nameYesThe pet's name, as it should be sung.
image_urlNoPublic URL to a photo of the pet: one pet, facing the camera, well lit. JPEG, PNG, WebP or HEIC, up to 15MB. Send this or photo.
relationshipNoWho the recipient is to the person buying it. 'myself' when it is for them.
recipient_nameNoWho the song is for, if it is a gift for someone else. Their first name is sung.

Output Schema

NameRequiredDescriptionDefault
idYes
tierYes
priceYes
styleYes
titleYes
voiceYes
lyricsYes
objectYes
statusYesdraft, previewing, preview_ready, preview_failed, paid, rendering, ready, render_failed or refunded.
paymentYes
speciesYes
languageYes
occasionYes
pet_nameYes
poll_urlYes
ready_atYes
next_stepYesWhat to do next, for the assistant.
photo_urlYes
video_urlYesThe HD MP4, once ready.
created_atYes
duration_sYes
manage_urlYes
checkout_urlYesWhere the person pays for the HD video. Present once the preview is ready.
credits_costYes
relationshipYes
gift_page_urlYesA page to send the recipient, once ready.
thumbnail_urlYes
recipient_nameYes
credits_refundedYes
preview_clip_urlYesA 5 second watermarked clip of the pet singing.
preview_audio_urlYesThe whole song as an MP3, free to play.
video_vertical_urlYes
checkout_expires_atYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.3/5.0
Behavior3/5

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

Annotations already declare the safety/mutation profile (readOnlyHint=false, destructiveHint=false, idempotentHint=false, openWorldHint=false), so no contradiction exists and the description's job is to add flow context. It does this well: free preview, 1-2 minute latency, paid HD video via a checkout link appearing once the preview is ready, credits alternative costing 100/200, and an immediate return of song id plus "previewing" status. That is genuinely useful beyond the annotations, though it does not cover failure modes (bad photo rejection, payment refusal handling).

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?

Front-loaded with the core action, then usage, then requirements, then timing and pricing, then return shape — a clean decision-ordered structure. Dense parentheticals (occasions, "the whole song plus a 5 second singing clip") carry real information rather than filler.

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 13-parameter tool with a nested photo object and an existing output schema, the description supplies exactly what the schema cannot: when to invoke, that required fields must be elicited from the user, expected latency, and the free-preview/paid-video commercial model. Return values are correctly left brief since an output schema exists.

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 description coverage is 100%, so the baseline is 3, but the description adds requirement-level meaning: a photo (image_url or attached photo), pet name, species and occasion are mandatory, and missing values must be requested rather than guessed. It also ties the payment/tier distinction to the commercial flow (free preview vs. bought HD video), which helps an agent reason about the enum beyond its literal wording.

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?

Specific verb and resource: "Write and record a custom song about a pet from one photo, then make a short preview of the pet singing it." It distinguishes the two-stage deliverable (song + singing preview) and, by framing it as the preview-producing tool, separates itself from create_singing_video and get_pet_song without needing to name them.

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 trigger conditions are given ("Use it when someone wants a personalised song or singing video of their own pet, for themselves or as a gift") with concrete occasions, plus a strong behavioural instruction to ask for missing inputs rather than invent them. It stops short of naming an alternative tool or a when-not-to-use case, which keeps it off a 5.

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