Photo Sheet

Turn a voice note into a table

voice_to_sheet

Use this when the user has a voice note that lists things (expenses, orders, stock counts, hours worked) and wants it as a table. Pass the attached audio as file, or audio_url, or audio_base64 (ogg, opus, m4a, mp3, wav, webm, flac or amr; up to about 3 minutes); add language when known. It transcribes the note with free speech-to-text, then copies it into rows and columns. Returns the table, the transcript, the values that may be misheard (unclear), sum checks, CSV text and 24-hour links. Not for meeting transcripts or subtitles.

Example tool call

This call uses example arguments supplied in the tool’s input schema.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "language": "en",
      "audio_base64": "T2dnUwACAAAAAAAAAAA="
    },
    "name": "voice_to_sheet"
  }
}

Input Schema

Name	Required	Description
`file`	No	The voice note the user attached in the chat.
`hint`	No	Optional: what the content is or which columns the person wants, for example 'stock count, item and quantity only'.
`language`	No	Optional ISO 639-1 code of the spoken language, such as en, vi, es or sw. Without it the language is detected.
`audio_url`	No	A public https link to one voice note (ogg, opus, m4a, mp3, wav, webm, flac or amr), up to 6 MB, about 3 minutes.
`audio_base64`	No	The audio bytes as base64, up to 6 MB.

Output Schema

Name	Required	Description	Default
`csv`	Yes
`kind`	Yes
`rows`	Yes
`links`	Yes
`notes`	Yes
`title`	Yes
`checks`	Yes
`notice`	Yes
`source`	Yes
`status`	Yes
`totals`	Yes
`columns`	Yes
`message`	Yes
`unclear`	Yes
`currency`	Yes
`transcript`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

First observedOct 21, 2026

TDQS

A4.7/5.0

Behavior5/5

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

Annotations only cover the safety profile (readOnly=false, openWorld=true, non-idempotent, non-destructive). The description adds substantial beyond-schema behavior: it uses free speech-to-text, applies the hint to column selection, flags possibly misheard values ('unclear'), performs sum checks, and returns links that expire in 24 hours.

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?

Three sentences, front-loaded with the trigger, then the input contract, then the outputs and the exclusion. Sentence order matches how an agent needs the information; there is no 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 5-parameter tool with nested file object, output schema, and annotations, the description covers trigger, input routes, format/size limits, hint behavior, return contents, and exclusions. Even though an output schema exists, summarizing the return shape (table, transcript, unclear values, CSV, links) adds useful orientation without bloat.

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 coverage is 100%, so baseline is 3, but the description adds real meaning by presenting file / audio_url / audio_base64 as interchangeable input routes ('or... or...'), listing supported formats and a ~3 minute limit, and explaining that language is optional and triggers auto-detection.

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?

Names a specific verb+resource ('Turn a voice note into a table') and enumerates concrete content types (expenses, orders, stock counts, hours worked). It also implicitly separates itself from photo_to_sheet and text_to_sheet by scoping to audio input.

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?

Provides an explicit trigger ('when the user has a voice note that lists things') and a clear exclusion ('Not for meeting transcripts or subtitles'). It does not explicitly name photo_to_sheet as the alternative for image input, so routing to siblings for other modalities is left implicit.

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

All Photo Sheet 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.