Skip to main content
Glama

Report a problem to Tofu

reportProblem

Report a problem in Tofu to its team. Requires confirmed: true, representing the person’s agreement to send this exact kind and message, knowing a person at Tofu reads every report, kept 180 days with the app’s status attached (unless includeAppDetails is false); without the literal nothing is sent. It covers a Tofu step failing again or a safety check stopping harmless code, not the app’s own failures, a refusal about the account’s plan, or a problem in the chat or editor in use. tool names the failing tool, and status and reference an HTTP status or a T- reference only when the person quotes one: this connection’s own answers carry neither. The input holds no key, password, settings value, code, log, app data, file path or conversation: Tofu removes email addresses and phone numbers with a + country code and attaches nothing else. Each account sends at most 5 a day, a refused one included; a repeat within 24 hours returns the first report. message says what happened.

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": {
      "kind": "<kind>",
      "message": "<message>",
      "confirmed": "<confirmed>"
    },
    "name": "reportProblem"
  }
}

Input Schema

NameRequiredDescriptionDefault
kindYes
toolNo
statusNo
messageYes
confirmedYes
projectIdNo
referenceNo
includeAppDetailsNo

Output Schema

NameRequiredDescriptionDefault
atYes
codeYes
messageYes
outcomeYes
receiptYes
removedYes
reportIdYes
referenceYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.3/5.0
Behavior5/5

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

Well beyond the annotations, it discloses that a person at Tofu reads every report, that reports are kept 180 days with the app's status attached, that email addresses and phone numbers with a + country code are stripped, that no key/password/settings/code/log/file path/conversation is accepted, and that each account is capped at 5 per day with a 24-hour dedup returning the first report. This is exactly the behavioral context the annotations cannot provide.

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

Conciseness3/5

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

Purpose is front-loaded, but the body is a single dense run-on paragraph stitched together with semicolons, parentheses, and backticked fragments. Nearly every clause carries real information, yet the lack of paragraph or bullet separation makes the privacy, rate-limit, and parameter facts hard to scan on first read.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

An output schema exists, so return values need not be explained, and consent, retention, redaction, and rate-limit behavior are all covered. The one substantive hole is `projectId`, which appears in the schema but is never mentioned or scoped in the description.

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 0% schema description coverage and 8 parameters, the description carries the burden and mostly does: it explains `confirmed`, `message` ('says what happened'), `tool` ('names the failing tool'), `status` and `reference` (an HTTP status or a `T-` reference only when the person quotes one), and `includeAppDetails` ('unless `includeAppDetails` is false'). `projectId` and the `kind` enum values are never given meaning, which is the remaining gap.

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 sentence gives a specific verb and resource ('Report a problem in Tofu to its team') and the description then delimits scope by naming what it does and does not cover (a Tofu step failing again or a safety check blocking harmless code, versus app failures, plan refusals, or chat/editor problems). The phrase 'a Tofu step failing again' is slightly ambiguous, which keeps this from a clean 5, but the tool's purpose is unmistakable.

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?

It states explicit inclusion criteria (Tofu step failing again, safety check stopping harmless code) and explicit exclusions (the app's own failures, a refusal about the account's plan, a problem in the chat or editor in use). It also makes the precondition concrete: 'Requires `confirmed: true` ... without the literal nothing is sent.'

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