List the most recently updated compliance nodes: the regulatory change feed. Use to monitor incoming amendments, new guidance, or freshly added rules. Filter by pillar to focus on a domain. Agents should call this on a schedule to keep compliance posture current.
| Name | Required | Description | Default |
|---|---|---|---|
| days | No | Look back N days. Default 30. Max 180. | |
| pillar | No | Optional pillar filter, e.g. "AI Governance" or "Cybersecurity". |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Beyond annotations (readOnly, openWorld), the description clarifies what counts as a change and advises on scheduling. It does not disclose return format or pagination, but given annotation coverage, this is sufficient for a 4.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Four sentences, each contributing: action/resource, use cases, filtering, and scheduling. No filler. Front-loaded with the verb and object.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a simple read-only feed with optional filters, the description covers the core usage and context. It lacks explicit output details, but the absence of an output schema and the tool's straightforward nature make this acceptable. Slight ambiguity about what 'updated' entails prevents a 5.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema already fully documents the two parameters. The description reinforces pillar's purpose ('focus on a domain') but adds no new semantics. Baseline 3 applies.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly identifies the action ('List') and resource ('compliance nodes'), positioning it as the 'regulatory change feed.' It implies a distinction from siblings like search_nodes or watch_changes, but does not explicitly name alternatives, so it falls short of a 5.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description provides explicit use cases: monitoring amendments, new guidance, or new rules, and recommends a scheduling pattern. It does not mention exclusions or alternative tools, so a 4.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.
Most tools target distinct functions: discovery, analysis, runs, attestation, and change feeds. However, get_latest_changes, obligation_deltas, and watch_changes all relate to regulatory changes and could be confused, as could get_node vs consult_node. Descriptions clarify, but boundaries are not always obvious.
The majority follow a verb_noun pattern (browse_topics, create_attestation, get_node), but there are deviations like drift_check, gap_check, obligation_deltas, oscal_assessment_results, and point_in_time, which break the convention. Mixed patterns make the API less predictable.
With 25 tools, the server is at the heavy end of the borderline range. Some tools (e.g., get_latest_changes vs obligation_deltas, get_run vs get_audit_pack) have overlapping functionality that could be consolidated, though the broad compliance domain justifies a larger surface.
The server covers discovery, analysis, run ledgers, attestation, and exports, but lacks a standalone way to access full node content outside a run (get_node returns only summaries; full nodes are external). This is a notable gap for compliance work. Also, there's no list of jurisdictions or verification tool for attestations, though these may be outside the server's intent.