Skip to main content
Glama
aethis-mcp

aethis-mcp

Official
by Aethis-ai

aethis_create_ruleset

Create a new ruleset from source text and required test cases for test-driven rule development. Use it before generating and testing the rules.

Instructions

Create a new rule ruleset with source text and test cases (TDD). Test cases are required. After creation, call aethis_generate_and_test.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "name": "<name>",
      "section_id": "<section_id>",
      "source_text": "<source_text>",
      "test_cases": "<test_cases>"
    },
    "name": "aethis_create_ruleset"
  }
}

Input Schema

NameRequiredDescriptionDefault
nameYesHuman-readable name for the rule ruleset
domainNoDomain hint (e.g., 'uk_immigration')
section_idYesUnique section identifier (e.g., 'flight_readiness')
test_casesYesTest cases with optional strict acceptance expectations.
source_textYesThe source legislation, policy, or specification text
contract_versionNoRequired when acceptance expectations, expected_review_bindings or retained_passages are supplied.
retained_passagesNoOptional list of source passages that must be retained in the rule notes. Each is {id, text} with text at most 2000 characters; matching ignores case, whitespace runs and typographic quotes and checks literal retention, not meaning.
expected_review_bindingsNoOptional review-binding catalogue; omit for no assertion or use {} to assert zero bindings.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changedv0.24.0
    • changedInput schema / properties / test_cases / items / properties / expectations / anyOf
      Previous value: -[
      -  {
      -    "additionalProperties": false,
      -    "properties": {
      -      "pending_reviews": {
      -        "additionalProperties": false,
      -        "properties": {
      -          "resolution_fields": {
      -            "items": {
      -              "type": "string"
      -            },
      -            "maxItems": 500,
      -            "type": "array"
      -          },
      -          "unmapped_count": {
      -            "maximum": 500,
      -            "minimum": 0,
      -            "type": "integer"
      -          }
      -        },
      -        "required": [
      -          "unmapped_count"
      -        ],
      -        "type": "object"
      -      },
      -      "useful_unknown_fields": {
      -        "items": {
      -          "$ref": "#/properties/test_cases/items/properties/expectations/anyOf/0/properties/pending_reviews/properties/resolution_fields/items"
      -        },
      -        "maxItems": 500,
      -        "type": "array"
      -      }
      -    },
      -    "type": "object"
      -  },
      -  {
      -    "type": "null"
      -  }
      -]New value: +[
      +  {
      +    "additionalProperties": false,
      +    "properties": {
      +      "field_errors": {
      +        "additionalProperties": {
      +          "type": "string"
      +        },
      +        "description": "Exact message the engine is expected to report for each field when an input invariant rejects the inputs. Only valid when expected_outcome is undetermined.",
      +        "type": "object"
      +      },
      +      "pending_reviews": {
      +        "additionalProperties": false,
      +        "properties": {
      +          "resolution_fields": {
      +            "items": {
      +              "type": "string"
      +            },
      +            "maxItems": 500,
      +            "type": "array"
      +          },
      +          "unmapped_count": {
      +            "maximum": 500,
      +            "minimum": 0,
      +            "type": "integer"
      +          }
      +        },
      +        "required": [
      +          "unmapped_count"
      +        ],
      +        "type": "object"
      +      },
      +      "useful_unknown_fields": {
      +        "items": {
      +          "$ref": "#/properties/test_cases/items/properties/expectations/anyOf/0/properties/pending_reviews/properties/resolution_fields/items"
      +        },
      +        "maxItems": 500,
      +        "type": "array"
      +      }
      +    },
      +    "type": "object"
      +  },
      +  {
      +    "type": "null"
      +  }
      +]
  2. Changed2 schema fields changedv0.23.0
    • changedInput schema / properties / contract_version / description
      Previous value: -"Required when acceptance expectations or expected_review_bindings are supplied."New value: +"Required when acceptance expectations, expected_review_bindings or retained_passages are supplied."
    • addedInput schema / properties / retained_passages
      Added value: +{
      +  "description": "Optional list of source passages that must be retained in the rule notes. Each is {id, text} with text at most 2000 characters; matching ignores case, whitespace runs and typographic quotes and checks literal retention, not meaning.",
      +  "items": {
      +    "additionalProperties": false,
      +    "properties": {
      +      "id": {
      +        "description": "Unique identifier for the passage",
      +        "type": "string"
      +      },
      +      "match": {
      +        "const": "normalized_contains",
      +        "type": "string"
      +      },
      +      "text": {
      +        "description": "Source text that must be retained",
      +        "type": "string"
      +      }
      +    },
      +    "required": [
      +      "id",
      +      "text"
      +    ],
      +    "type": "object"
      +  },
      +  "maxItems": 100,
      +  "type": "array"
      +}
  3. First observedv0.22.0

TDQS

A3.6/5.0
Behavior3/5

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

Annotations already declare readOnlyHint=false, idempotentHint=false, destructiveHint=false and openWorldHint=true, so the mutation profile is known without the description. The description adds the TDD requirement and the post-creation hand-off, but says nothing about failure modes (e.g. duplicate names or section_ids given idempotentHint=false) or what happens to a partially created ruleset.

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?

Three short, front-loaded sentences with no filler; the required-input constraint and next action come before any elaboration. Minor redundancy in "rule ruleset" but nothing wasteful.

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?

For an 8-parameter, nested-object creation tool with no output schema, the description omits what the call returns (presumably a ruleset identifier) even though that value is needed to drive the instructed aethis_generate_and_test call. The essential workflow is conveyed, but the return contract and idempotency/conflict behavior are left implicit.

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%, so the schema already explains name, section_id, source_text, test_cases, contract_version, retained_passages and expected_review_bindings in detail. The description only restates that source_text and test_cases are needed and adds no semantics for the conditional contract_version or the optional binding catalogue, so baseline 3 is appropriate.

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?

States a concrete verb and resource: create a new ruleset from source text plus test cases in a TDD flow. It is distinguishable from list/discover/archive siblings by the creation verb and the required inputs, though it does not explicitly differentiate itself from the nearby aethis_create_rulebook.

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

Usage Guidelines4/5

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

Gives an explicit prerequisite ("Test cases are required") and a mandatory follow-up step ("After creation, call aethis_generate_and_test"), which is real sequencing guidance. It stops short of naming when to prefer this over aethis_create_rulebook or how to proceed if test cases are not yet designed.

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