Gravity

Upload a recording

upload_audio

Read-only

Get a link to upload a recording that's over 2 MB and isn't already online, up to 100 MB. PUT the file's bytes to upload_url (e.g. curl -T memo.m4a '<upload_url>'), then pass upload_id to transcribe_audio or add_voice_note. For a smaller file, pass audio_base64 to those tools instead; for one already online, audio_url. The link works for 15 minutes; the upload_id for a day. The recording is deleted once it's transcribed.

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": "upload_audio"
  }
}

Input Schema

Name	Required	Description	Default
No arguments

Output Schema

Name	Required	Description
`method`	Yes
`example`	Yes	A curl command that uploads memo.m4a.
`max_bytes`	Yes
`upload_id`	Yes	Pass to transcribe_audio or add_voice_note.
`expires_at`	Yes	When upload_url stops taking uploads.
`upload_url`	Yes	PUT the file here.

Schema Changelog

Changes observed during successful MCP inspections.

First observedNov 13, 2026

TDQS

A4.9/5.0

Behavior5/5

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

Goes well beyond the annotations by disclosing lifecycle and timing behavior: the link expires in 15 minutes, the upload_id lasts a day, and the recording is deleted once transcribed. It also gives the concrete handoff protocol (PUT the bytes to upload_url, e.g. a curl -T command), which annotations cannot express.

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?

Opens with the eligibility constraint, then the action, then the alternatives, then the expiry/lifecycle facts. Every sentence carries a distinct fact; even the curl example is functional rather than decorative.

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-parameter tool with an output schema, this covers everything an agent needs: size thresholds, the upload mechanism, expiry windows, how the result feeds transcribe_audio/add_voice_note, and the eventual deletion. Nothing material is left to inference.

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?

With zero input parameters the schema carries nothing to explain, and the description usefully documents the two handles this tool produces (upload_url for the PUT body, upload_id for downstream calls). The only gap is that it doesn't say what the response object looks like, though an output schema exists to cover that.

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 ('Get a link to upload a recording') and immediately qualifies it with the exact eligibility rules: over 2 MB, not already online, up to 100 MB. An agent can tell this apart from transcribe_audio and add_voice_note purely from this sentence.

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?

Explicit routing is given in both directions: use this tool for large/not-yet-online files, and 'pass audio_base64 to those tools instead' for smaller files or 'audio_url' for files already online. When-to-use, when-not-to-use, and the named alternatives are all present.

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?