Skip to main content
Glama

List obligations

get_obligations
Read-onlyIdempotent

Filter the obligation register (obligation → artefact → stack layer, with stable ids such as AIGE-OBL-EUAIA-ART9). All filters are optional and combine with AND. framework: an id, short name or name ("eu-ai-act", "EU AI Act", "ISO 42001", "nist"); role: a duty holder such as "provider", "deployer", "developer" or "GPAI provider" (matched in the duty holder, or in the scope of laws that name who they bind; rows with neither, such as voluntary standards, drop out); systemClass: an EU AI Act class (all-ai-systems, prohibited, high-risk-annex-iii, high-risk-annex-i, transparency-art50, gpai, gpai-systemic); appliesBefore: an ISO date, keeping rows whose first application date (appliesFrom) is on or before it (later milestones are listed with each row); status: in-force, applies-later, deferred, grace, voluntary or pending; layer: a stack layer 1-5.

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": "get_obligations"
  }
}

Input Schema

NameRequiredDescriptionDefault
roleNoDuty holder, e.g. "provider", "deployer".
layerNoStack layer, 1 to 5.
limitNoMaximum number of rows to return.
statusNoApplication status.
frameworkNoFramework id or name.
systemClassNoEU AI Act system class id.
appliesBeforeNoISO date (YYYY-MM-DD).

Output Schema

NameRequiredDescriptionDefault
totalYes
noticeYesIllustrative, not legal advice and not a claim of conformity.
sourceYesCanonical URL of the page this answer comes from; cite it.
datasetYesURL of the open-data document the answer was read from.
filtersYes
licenseYesLicence of the data (CC BY 4.0, attribution required).
returnedYes
dataVersionYesBody of Knowledge version of the data.
obligationsYes
frameworkIdsYesFramework ids the framework filter resolved to.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4/5.0
Behavior4/5

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

Annotations already declare readOnlyHint, idempotentHint and non-destructive behavior, so the safety profile is covered. The description then adds genuinely non-obvious semantics: role matching also searches the scope of laws that name their duty holders, rows with neither drop out, and appliesBefore keys on the first application date with later milestones shown per row. The main omission is the default result limit (25) and any ordering, which matter for a list tool.

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?

Front-loaded with the resource and id format, then semicolon-delimited per-filter clauses in the same order as the schema, with no filler. It is a single dense paragraph, however, and would scan faster as a list; the limit parameter is never mentioned despite being one of the seven.

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 no explanation, and the description thoroughly covers filter semantics for a seven-parameter tool with zero required parameters. The remaining gap is result-set behavior: default limit, ordering, and whether unpaged results are truncated.

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?

Schema coverage is 100% but the schema has no enumerated values and only terse one-line descriptions, so the description carries the real burden and does: it lists accepted framework forms ("eu-ai-act", "EU AI Act", "ISO 42001", "nist"), the six systemClass ids, the six status values, and the exact date semantics for appliesBefore. This is meaningful interpretation the schema does not provide.

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?

Opens with a specific verb and resource: "Filter the obligation register," and names the underlying model (obligation → artefact → stack layer) plus an example id format. It clearly reads as a filtered list operation, though it never explicitly distinguishes itself from the sibling get_obligation or explains that results are a collection rather than a single record.

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?

"All filters are optional and combine with AND" tells the agent how filters compose and implies no default restriction, which is useful. But there is no explicit when-to-use guidance, no statement of what an unfiltered call returns, and no routing to alternatives such as get_obligation for a single record or search_bok for full-text lookup.

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.