Probative legal-marketing data

Confirmed changes to the rules

list_rule_changes

Read-onlyIdempotent

Confirmed changes to the lawyer advertising rules dataset, newest first, each with its date, state, the cells it touched and its primary source. Optional since (YYYY-MM-DD).

Input Schema

Name	Required	Description	Default
`since`	No	Only changes on or after this day

Output Schema

Name	Required	Description
`meta`	Yes	Credit line (attribution), citation, DOI, version, license (CC BY 4.0), disclaimer, notice and the page to cite
`nextCursor`	No	Pass as `cursor` to get the next page; null on the last page
`provenance`	Yes	Where this came from: the publisher of the dataset, the dataset and its version DOI, the record id, the original source (who published it and its URL), the day that source was last checked, and when this answer was retrieved

Schema Changelog

Changes observed during successful MCP inspections.

Changed3 schema fields changedOct 27, 2026

addedOutput schema / properties / nextCursor

Added value: +{
+  "description": "Pass as `cursor` to get the next page; null on the last page",
+  "type": [
+    "string",
+    "null"
+  ]
+}

addedOutput schema / properties / provenance

Added value: +{
+  "description": "Where this came from: the publisher of the dataset, the dataset and its version DOI, the record id, the original source (who published it and its URL), the day that source was last checked, and when this answer was retrieved",
+  "properties": {
+    "citeUrl": {
+      "description": "The page to cite",
+      "type": [
+        "string",
+        "null"
+      ]
+    },
+    "dataset": {
+      "description": "Dataset id",
+      "type": "string"
+    },
+    "datasetTitle": {
+      "type": "string"
+    },
+    "dateChecked": {
+      "description": "YYYY-MM-DD the record was last checked against its source",
+      "type": [
+        "string",
+        "null"
+      ]
+    },
+    "doi": {
+      "description": "Version DOI",
+      "type": [
+        "string",
+        "null"
+      ]
+    },
+    "doiUrl": {
+      "type": [
+        "string",
+        "null"
+      ]
+    },
+    "line": {
+      "description": "The same facts as one sentence, to quote under an answer",
+      "type": "string"
+    },
+    "publisher": {
+      "description": "Publisher of the dataset",
+      "type": "string"
+    },
+    "recordId": {
+      "description": "Stable id of the record",
+      "type": [
+        "string",
+        "null"
+      ]
+    },
+    "retrievedAt": {
+      "description": "ISO 8601 time this answer was served",
+      "type": "string"
+    },
+    "source": {
+      "description": "The original source: statute, rule, bar opinion, court report, agency table or platform policy",
+      "type": [
+        "string",
+        "null"
+      ]
+    },
+    "sourceKind": {
+      "description": "primary or secondary",
+      "type": [
+        "string",
+        "null"
+      ]
+    },
+    "sourceUrl": {
+      "type": [
+        "string",
+        "null"
+      ]
+    },
+    "status": {
+      "description": "P primary source, S secondary, D default (no specific rule found), U open question",
+      "type": [
+        "string",
+        "null"
+      ]
+    },
+    "version": {
+      "description": "Dataset version",
+      "type": "string"
+    }
+  },
+  "required": [
+    "publisher",
+    "dataset",
+    "version",
+    "retrievedAt"
+  ],
+  "type": "object"
+}

changedOutput schema / required

Previous value: -[
-  "meta"
-]New value: +[
+  "meta",
+  "provenance"
+]

First observedOct 26, 2026

TDQS

B3.2/5.0

Behavior3/5

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

Annotations already declare readOnly, idempotent, non-destructive and closed-world, so safety is covered. The description adds two real behavioral facts beyond that: results are ordered newest first and only 'confirmed' changes are returned — but it says nothing about volume, pagination, or whether the full history is returned unprompted.

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?

One front-loaded sentence that states dataset, ordering, and return fields, plus a short parenthetical on the lone parameter. The field enumeration lightly duplicates the output schema, but nothing is padded.

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?

With an output schema, rich annotations, and a single fully-described parameter, the description covers what the agent needs. The remaining gap is the absence of any statement about result limits or whether a bare call returns the entire history.

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?

Schema description coverage is 100% and the single parameter is already documented as 'Only changes on or after this day' with a pattern. The description merely restates the YYYY-MM-DD format, adding no new semantics such as inclusive/exclusive edge behavior. Baseline 3 applies.

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?

Names the specific resource (confirmed changes to the lawyer advertising rules dataset) and its ordering (newest first), which is enough to tell it apart from search_rules, get_rule, or whats_new. It never states an explicit verb such as 'list', leaving the agent to infer the operation from the title, but the resource scope is unambiguous.

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

Usage Guidelines2/5

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

No guidance on when to call this versus siblings like whats_new or list_datasets, which are the obvious near-neighbors. The only usage signal is the optional `since` note, so the agent must guess the context on its own.

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

All Probative legal-marketing data tools Inspect

Try in Browser

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources

Need Help?