Skip to main content
Glama

Create Knowledge Upload

create_knowledge_upload

Send a file from the user's own computer into a notebook, for a client that can run a command there (Codex, Claude Code, Cursor): a recording to transcribe (.mp3 .m4a .wav .ogg .webm .flac .mp4 .mpeg .mpga, WhatsApp voice notes .opus, .aac .amr .3gp .3ga .wma .oga) or a document (.pdf .docx .txt .md .csv .tsv), up to 1 GB. Give the file name and its exact size_bytes, and sha256 when you can. Returns an upload_url and ready commands: one curl PUT for a file up to 32 MB, else a short Python script that sends 32 MB chunks with Content-Range and resumes after an interruption. Run the command on the computer that holds the file; the bytes never pass through the conversation. Without notebook_id a new notebook named after the file (or title) is made when the last byte arrives. A recording takes one place in the account's transcription allowance, which depends on its plan and renews with its credits; the reply says how many places are left. Follow it with get_knowledge_upload.

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": {
      "filename": "<filename>",
      "size_bytes": "<size_bytes>"
    },
    "name": "create_knowledge_upload"
  }
}

Input Schema

NameRequiredDescriptionDefault
titleNoTitle for the new notebook, when notebook_id is omitted.
app_idNoOptional app whose notebooks to use. Omitted: the owner's own Business Brain.
sha256NoOptional hex sha256 of the file; a mismatch is refused.
filenameYesThe file's name with its extension, e.g. meeting-11-12.m4a.
folder_idNoFolder for the new notebook.
size_bytesYesThe exact file size in bytes.
notebook_idNoOptional: an existing notebook. Omitted: a new one.
content_typeNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

A4.2/5.0
Behavior3/5

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

Annotations already declare readOnlyHint=false, destructiveHint=false, idempotentHint=false and openWorldHint=false, so the safety profile is covered. The description still adds substantial context beyond that: the 1 GB cap, the 32 MB curl-vs-chunked-Python split, resume behavior, that bytes never traverse the conversation, that a notebook is created only when the last byte arrives, and that a recording consumes a transcription slot. Rich, but the annotations carry part of the burden.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

A single dense paragraph, but it is front-loaded with the core action and format list before the mechanics. The long parenthetical format enumerations are bulky yet functional; nothing is truly redundant.

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?

No output schema exists, and the description compensates by describing the return payload (upload_url, ready-to-run commands, remaining transcription allowance). For an 8-parameter tool with a multi-step upload flow, an agent has everything needed to call it and follow up.

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 88%, so the baseline is 3, and the description adds real meaning on top: filename plus exact size_bytes are required, sha256 is optional but a mismatch is refused, and omitting notebook_id creates a new notebook named after the file or title. It does not explain app_id, folder_id, or content_type, which is the remaining gap.

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 ('Send a file from the user's own computer into a notebook') and scopes it to clients that can run a command locally, which separates it from server-side ingestion siblings like add_knowledge_document or import_knowledge_audio_url. Supported formats and the 1 GB ceiling are spelled out.

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?

Gives a clear precondition (the client must be able to run a command on the machine holding the file) and an explicit next step ('Follow it with get_knowledge_upload'). It does not explicitly say when to prefer a different ingestion tool, but the local-file constraint effectively routes the agent.

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