Skip to main content
Glama

Run safety check

scan
Read-onlyIdempotent

Run Tofu’s safety check on this project through the shared backend. The result’s coverage and verdict describe the scope of the pre-deploy tripwire plus a fixed set of deterministic rules over the files Tofu holds for the project. It matches the malware shapes it knows — obfuscated execution, install-time downloads, secret exfiltration, wallet draining, clone-time hooks, curated bad dependency versions — and NOTHING MORE, so pass: true never means the code is safe. coverage states how many files were read of how many were given, which checks ran, and what none of them looks for; verdict says the same in one sentence. pass: true with coverage.inspected: 0 means nothing was inspected, which is not a pass. This result is not a security clearance, and pass is not a statement that the code is safe. mobileReadiness is static metadata, not a safety or device verdict.

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": {
      "projectId": "<projectId>"
    },
    "name": "scan"
  }
}

Input Schema

NameRequiredDescriptionDefault
projectIdYes

Output Schema

NameRequiredDescriptionDefault
passYes
verdictNo
coverageNo
findingsYes
scannedFilesYes
mobileReadinessNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A3.6/5.0
Behavior4/5

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

Annotations already declare readOnly/idempotent/non-destructive, so the description isn't burdened with safety disclosure. Instead it adds genuinely useful behavioral context beyond them: the fixed rule set it matches, that `pass: true` does not mean safe, and that `coverage.inspected: 0` is not a pass. This is meaningful disclosure about the tool's scope limits, though it omits runtime/auth behavior.

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?

The purpose is front-loaded, which is good, but the disclaimer that `pass` is not a safety guarantee is restated at least four times, and the `coverage`/`verdict` fields are explained in three overlapping sentences. Roughly half the text could be cut without losing information.

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, yet the description still explains what `coverage`, `verdict`, and `mobileReadiness` mean in interpretive terms — arguably beyond what's needed, but not harmful. Combined with the explicit non-clearance caveats, an agent has enough to call and interpret this tool correctly; only projectId semantics are thin.

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

Parameters3/5

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

There is one parameter (`projectId`) with 0% schema description coverage, so the description carries the burden and only implies it by saying the check runs "on this project." It doesn't state the id format, where to obtain it, or what happens with an unknown id.

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 description states a specific verb and resource: "Run Tofu's safety check on this project through the shared backend." It's clear this is a scan/audit operation, though it doesn't explicitly distinguish itself from any sibling tool (largely auth/sharing/database tools, so overlap is naturally low).

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Usage is only implied via "pre-deploy tripwire" — an agent can infer it's meant to run before deploys. There is no explicit when-to-use statement, no prerequisites (e.g., does the project need building first?), and no named alternative to compare against.

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