Skip to main content
Glama
SVerITG

Metis

by SVerITG
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Local

Metis · Data Guardian — Check Data Safety

check_data_safety

Scan pasted or shared data for personal identifiers before any analysis, returning safety status, warnings, and next steps so sensitive records can be masked or handled safely.

Instructions

Check pasted or shared data for personal identifiers — call FIRST, before analysing it.

Call this as the very first step whenever the researcher pastes or shares
rows about individual people (a line list, patient or participant records,
a table with names, dates of birth, phone numbers, GPS points or IDs) —
before any calculation or answer, even for a simple question. If the result
is not PUBLIC, do not analyse the raw rows: mask them with anonymize_text,
log the event with log_consent_event, and offer a script the researcher
runs locally.

Returns safety status, classification, specific warnings and the next steps.

Args:
    content: Text content to scan.
    file_path: Optional file path for context-based classification.

Input Schema

NameRequiredDescriptionDefault
contentYes
file_pathNo

Output Schema

NameRequiredDescriptionDefault
resultYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A4.6/5.0
Behavior4/5

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

With no annotations, the description carries the full behavioral burden. It discloses what the tool returns (safety status, classification, warnings, next steps) and prescribes a conditional next action based on the result. It does not explicitly state whether the tool is read-only or whether it has side effects, but the 'check' framing and subsequent logging via a separate tool strongly imply it is non-mutating. A 4 reflects strong but not exhaustive disclosure.

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?

The description is front-loaded with the imperative 'call FIRST' and structured logically (purpose, when to call, what to do based on result, return values, args). Slightly verbose but every sentence adds useful information, and 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?

Given the tool's safety-critical role, no annotations, and an existing output schema, the description provides everything an agent needs: precise triggering conditions, conditional next steps, return summary, and parameter meanings. No critical gaps remain.

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 0% (no parameter descriptions), so the description must compensate. It does: 'content: Text content to scan' and 'file_path: Optional file path for context-based classification' add meaning beyond the bare titles. It could specify expected file path format, but the core semantics are clear.

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?

The description states a specific verb ('check') and resource ('pasted or shared data for personal identifiers'), and explicitly distinguishes this tool from later steps in the workflow (anonymize_text, log_consent_event). An agent can immediately tell what the tool does and why it exists.

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 gives explicit when-to-use guidance ('call FIRST, before analysing', 'whenever the researcher pastes or shares rows about individual people'), when-not-to-analyse guidance ('if the result is not PUBLIC, do not analyse the raw rows'), and names alternatives ('mask them with anonymize_text, log the event with log_consent_event'). This is a complete usage recipe.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Deploy Server

Other Tools