Skip to main content
Glama

Upload attached file

ingestAttachment
Destructive

Send a file the person attached in this chat to Tofu as an app’s code: file is the attachment as the chat passes it, by link; Tofu downloads it only from the chat’s own file store, at most 10 MB. The attachment is the whole app: a ZIP is the app’s folder, any other file its one file, at path (else index.html for an HTML file, or its own name). Send name to make a new app, or projectId to replace all the code of an app this account owns (a repository-linked app’s current source too) with this attachment — a file not in it is not in the new version. A ZIP with an unsafe path or a private file anywhere in it (a .env, a key) is refused with a sentence and nothing is stored. The same name with the same file again within ten minutes answers with the app already made (reused: true) and makes no second one. summary is one plain line on what this code changes, never a secret.

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": {
      "file": "<file>"
    },
    "name": "ingestAttachment"
  }
}

Input Schema

NameRequiredDescriptionDefault
fileYes
nameNo
pathNo
summaryNo
projectIdNo

Output Schema

NameRequiredDescriptionDefault
noteNo
bytesYes
filesYes
reusedNo
sha256Yes
receivedYes
projectIdYes
latestDeploymentNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A3.9/5.0
Behavior3/5

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

Annotations already declare destructive=true, readOnly=false and openWorld=true, so the safety profile is covered; the description still adds real value with the 10 MB cap, the refusal rule for unsafe ZIP paths or private files, and the ten-minute dedupe returning reused:true. However, that dedupe window sits awkwardly against idempotentHint=false without reconciliation, and it does not say what the caller must supply for authentication or ownership checks on projectId.

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?

Purpose is front-loaded in the opening clause and every subsequent sentence adds a distinct rule (size, ZIP mapping, create vs replace, refusal, dedupe, summary). The em-dash-heavy clause chaining makes it denser than necessary and harder to scan than a short bulleted structure would be, but 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 destructive, nested-object ingestion tool this covers the load-bearing details: source restriction, size limit, archive-to-app mapping, replace consequences ('a file not in it is not in the new version'), refusal behavior, and dedupe. An output schema exists, so return-value documentation is correctly left out.

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 description coverage is 0%, so the description must carry the load, and it explains file (pass-through attachment by link), path (with index.html and own-name defaults), name, projectId (replace-all semantics) and summary (one plain line, no secrets). The nested AttachedFile fields (file_id, file_name, mime_type, download_url) are not described, leaving the shape of the required object to the schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The first clause gives a specific verb and resource: send a chat attachment to Tofu as an app's code. It also constrains the source (only the chat's own file store, by link), which functionally separates it from ingestFiles and ingestPublicRepository without naming them. A sibling name is never cited explicitly, so it stops short of a 5.

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?

Clear branch guidance: send `name` to create a new app, or `projectId` to replace all code of an owned app. It also implies the when-not via the 10 MB cap and the chat-file-store restriction. It never explicitly routes the agent to ingestFiles or ingestPublicRepository for other sources, so alternatives are inferred rather than stated.

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