Media Generator — Images, Videos & Audios

song_generator

Input: Lyrics text and required tags (music categories/genres) for song generation.

Output: We will return the generated song URL and details to the user.

Functionality: This tool generates a custom song from provided lyrics. It creates original music that matches the style, mood, and tone specified by the tags. Tags must include music categories such as "rock", "pop", "jazz", "hip hop", "country", etc.

Steps:

We will get the user_id from the request context.
We will validate the user's generation tokens.
We will call the Lyrics to Melody API with the provided lyrics and parameters.
This API will return a JSON response with the generated song URL and details.
We will return the song URL and details to the user.

INSTRUCTION FOR CLIENT MODEL:

Extract the required input parameters 'lyrics' (type: string) and 'tags' (type: string, music categories/genres).
Tags must include music categories like "rock", "pop", "jazz", "hip hop", "country", "electronic", etc. Multiple tags can be combined (e.g., "rock pop" or "jazz blues").
Optional parameters: 'title' (default: "Melody"), 'language' (default: "English"), 'country' (default: "US"), 'audio_duration' (default: 0), 'ref_file_url' (reference audio URL, optional), 'ref_audio_strength' (0.0-1.0, default: 0.0).
Ignore any extraneous information in the user's input.
Pass the extracted values to this tool.
Example: For user input "Create a rock song with these lyrics: 'Walking in the rain, feeling the pain'", extract 'lyrics' as 'Walking in the rain, feeling the pain' and 'tags' as 'rock'.

Input Schema

TableJSON Schema

Name	Required	Default
`tags`	Yes
`title`	No	Melody
`lyrics`	Yes
`country`	No	US
`language`	No	English
`ref_file_url`	No
`audio_duration`	No
`ref_audio_strength`	No

Output Schema

TableJSON Schema

Name	Required	Description	Default
`result`	Yes

TDQS

A4.2/5.0

Behavior4/5

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

No annotations are provided, so the description carries full responsibility. It discloses internal steps: getting user_id from context, validating generation tokens, calling the Lyrics to Melody API, and returning the song URL and details. It also mentions defaults for optional parameters and instructs to ignore extraneous input. This is substantial, though it doesn't discuss error handling or failure modes.

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 description is organized into clear sections (Input, Output, Functionality, Steps, Instruction) which aids scannability. However, it is verbose—the tag requirements are repeated, and the Steps section partially restates the Functionality. The client instruction block, while useful, adds length and is tangential to the core tool description.

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?

Given the absence of annotations and the presence of an output schema, the description is thoroughly complete. It covers required and optional parameters, internal workflow, token validation, and expected output. An agent has all necessary information to invoke the tool correctly and anticipate the response.

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

Parameters5/5

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

Schema coverage is 0%, so the description fully compensates. It explains 'lyrics' and 'tags' in detail, including tag formats and examples, and lists all optional parameters with defaults (title='Melody', language='English', country='US', audio_duration=0, etc.). The example extraction clarifies how to interpret user input, providing semantics far beyond the bare schema.

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 clearly states the tool generates a custom song from provided lyrics, with tags specifying the style/mood/tone. It uses specific verbs ('generates', 'creates original music') and identifies the resource (lyrics + tags), distinguishing it from generic music generation. Though it doesn't name siblings, the unique input of lyrics makes the purpose unmistakable.

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 description implies usage when a user wants a song from lyrics with given tags, and it details parameter extraction. However, it lacks explicit guidance on when not to use this tool or how it contrasts with sibling tools like 'music_generator'. The 'Instruction for client model' focuses on parameter extraction rather than tool selection context.

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

All Media Generator — Images, Videos & Audios tools Inspect

Try in Browser

RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

TDQS

A3.9/5.0

Disambiguation4/5

Most tools have clearly distinct purposes, such as generate_image, remove_background, and upscale_image. However, logo_generator and generate_image both accept a text prompt and return an image URL, which could cause confusion, and music_generator and song_generator overlap in audio generation, though their inputs differ.

Naming Consistency3/5

Tool names are a mix of verb_noun (generate_image, remove_background), noun_generator (logo_generator, song_generator), and simple verbs (fetch, search, health). While readable, the lack of a single consistent pattern makes it less predictable for an agent.

Tool Count4/5

With 17 tools, the server is slightly above the ideal 3-15 range but not excessively over. Each tool serves a distinct function for generating or manipulating media, so the count feels justified for the broad scope.

Completeness4/5

The toolset covers the core media generation lifecycle: image generation, editing, background removal, upscaling, video generation, image-to-video, music and song generation, and text-to-speech. Minor gaps like video editing or managing past generations exist, but they are not critical for standard workflows.

Resources

Need Help?