Gravity

Add a voice note

add_voice_note

Transcribe a recording (through AssemblyAI) and save it as a new note at the top of the user's Gravity list, the way the app's mic does. Use it for "save this voice memo to Gravity"; to get the words without saving, use transcribe_audio. A tag spoken first with a pause becomes the note's tag; tag sets one instead. If no speech is heard, nothing is saved and it returns an error.

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": "add_voice_note"
  }
}

Input Schema

Name	Required	Description
`tag`	No	Adds a tag prefix, e.g. "todo". Leave out to keep a spoken one.
`keywords`	No	Names or rare words in the recording, spelled as they should be written.
`language`	No	The spoken language as a code, e.g. en, de, ja. Leave out to detect it.
`audio_url`	No	An https link to the recording (WAV, M4A, MP3, FLAC, OGG, WebM and most other audio or video formats).
`upload_id`	No	The upload_id from upload_audio, once the file has been PUT to its upload_url.
`audio_base64`	No	The recording itself, base64-encoded, up to 2 MB (a few minutes of compressed audio). For a larger file, use upload_audio and pass upload_id.

Output Schema

Name	Required	Description	Default
`note`	Yes
`outcome`	Yes	unchanged: the note was already like that, so nothing was written.

Schema Changelog

Changes observed during successful MCP inspections.

First observedNov 13, 2026

TDQS

A4.6/5.0

Behavior5/5

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

Annotations already disclose write/open-world/non-idempotent behavior, and the description adds useful context beyond that: AssemblyAI dependency, top-of-list placement, spoken-tag handling, tag override, and the no-speech failure behavior. This gives the agent a clear picture of side effects and edge cases.

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?

The description is three tight sentences, front-loading the core action and then adding the alternative, tag behavior, and failure case. Every sentence carries useful information with no repetition.

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?

It covers the core behavior, sibling routing, tag override, and a key error case, and the output schema handles return values. The one notable gap is that with six optional parameters and zero required fields, it never states that at least one audio source must be provided.

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 100%, so the input schema already documents the audio input options, keywords, language, and tag parameters. The description adds some tag/spoken-tag interaction detail, but it does not clarify that an audio source must be supplied or how audio_url, upload_id, and audio_base64 relate as alternatives.

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 states a specific verb+resource+outcome: transcribe a recording and save it as a new note at the top of the user's Gravity list. It also explicitly distinguishes itself from transcribe_audio, so the agent can select it without opening sibling schemas.

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?

It gives an explicit use case ("save this voice memo to Gravity") and names the alternative when the goal is transcription only: transcribe_audio. The when-to-use distinction is clear and directly actionable.

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

All Gravity tools Inspect

Try in Browser

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources

Need Help?