Skip to main content
Glama

evidence_gaps

Read-only

Identify AI use cases with missing EU AI Act compliance evidence, prioritized by risk tier, and filter results by department, obligation, data processing, or end-of-life date.

Instructions

AI use cases with missing compliance evidence, strictest tier first.

tier: prohibited, high, limited or minimal. obligation: an ID or words from its title, e.g. 'oversight', 'logs', 'D-WORKERS'. end_of_life_before: ISO date.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "evidence_gaps"
  }
}

Input Schema

NameRequiredDescriptionDefault
tierNo
departmentNo
obligationNo
end_of_life_beforeNo
processes_personal_dataNo

Output Schema

NameRequiredDescriptionDefault
resultYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A3.5/5.0
Behavior3/5

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

Annotations already declare readOnlyHint=true and openWorldHint=false, so the safety profile is covered. The description adds one genuine behavioral fact beyond that—the strictest-tier-first ordering—but says nothing about result limits, pagination, or whether an empty result means 'no gaps' versus 'no matching use cases'.

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 purpose is front-loaded in one line and the parameter notes are terse and scannable. The telegraphic style ('obligation: an ID or words from its title') costs a little clarity but wastes no words.

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

Completeness3/5

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 described, and the annotations cover the read-only nature. The gaps are the two undocumented filters (department, processes_personal_data) and the absence of any statement about behavior when all filters are omitted, which matters for a zero-required-parameter tool.

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 carries the full burden and largely meets it: tier is enumerated ('prohibited, high, limited or minimal'), obligation is explained with matching examples ('oversight', 'logs', 'D-WORKERS'), and end_of_life_before is given a concrete format (ISO date). Two parameters, department and processes_personal_data, remain entirely undefined.

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 resource and scope: 'AI use cases with missing compliance evidence', plus an ordering rule ('strictest tier first'). That is concrete enough to know what comes back, but it does not distinguish this from siblings like portfolio_exposure or obligations_for_use_case, which plausibly surface overlapping evidence data.

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?

The phrase 'missing compliance evidence' implies the audit/gap-analysis context in which to reach for this tool, and the sort order hints at triage. However, there is no explicit when-not guidance and no named alternative for related questions such as portfolio-wide exposure or per-use-case obligations.

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