Skip to main content
Glama

Upload app files from chat

ingestFiles
Destructive

Send an app’s code to Tofu as files from this chat. The files sent are the whole app: name makes a new app, or projectId replaces all the code of an app this account owns — its address, settings and earlier versions stay, but a file not sent is not in the new version, so an update requires the app’s complete current code. For an app that follows a GitHub repository, its next push then pauses automatic updates. summary is one plain line on what this code changes, shown as the version’s title on the Versions page; never a secret. One call takes at most 500 files, 1536 KB in all and 512 KB per file, and 512 KB of base64 files together; a call past a limit or with a private file (a .env, a key) is refused with a sentence and nothing is stored. The answer’s files counts what Tofu keeps. The same name with the same files again within ten minutes answers with the app the first call made (reused: true) and makes no second one.

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": {
      "files": "<files>"
    },
    "name": "ingestFiles"
  }
}

Input Schema

NameRequiredDescriptionDefault
nameNo
filesYes
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

A4.7/5.0
Behavior5/5

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

Goes well past the annotations: it spells out exactly what is destroyed on update ('a file not sent is not in the new version'), what survives ('address, settings and earlier versions'), the refusal behavior for limit violations and private files ('nothing is stored'), and a ten-minute dedupe window returning `reused: true`. This is the destructiveHint=true behavior made concrete rather than merely asserted.

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?

Dense but front-loaded, with the create/update distinction and the update-completeness warning leading. It is a single unbroken paragraph mixing routing, limits, refusal semantics, and dedupe, so scanning for a specific rule takes work; a lightweight structure would help.

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 mutation tool this covers what an agent needs: ownership requirement, full-replacement semantics, size and count limits, refusal behavior, and the `reused` and `files` fields of the response. With an output schema present, it does not need to enumerate return values further.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters5/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Top-level schema coverage is 0%, so the description carries the load and does: `name` creates a new app, `projectId` replaces an owned app's code, `summary` becomes the version title on the Versions page and must never be a secret. It also bounds `files` behaviorally with concrete limits (500 files, 1536 KB total, 512 KB per file and per base64 group), which the schema does not express.

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 an app's code to Tofu as files from this chat') and immediately splits the two modes by parameter: `name` creates, `projectId` replaces. An agent can tell this apart from attachment or repository ingestion tools without opening the schema.

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?

Explicitly says which parameter selects create vs. update and warns that an update requires the app's complete current code, plus the GitHub-follow interaction. It does not name any sibling (e.g., an attachment or public-repository ingest tool) as the alternative, so routing for non-app files is left to inference.

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