get_rule_sourceFetch a domain's rule set as editable YAML (plus the parsed rules and
whether you may edit it). Use this before put_rules to see the current
rules; the built-in demo domains are read-only.
| Name | Required | Description | Default |
|---|---|---|---|
| domain | Yes |
| Name | Required | Description | Default |
|---|---|---|---|
| result | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The annotation already indicates readOnlyHint=true, but the description adds beyond that by disclosing the tool returns editable YAML, parsed rules, and an editability flag. It also notes demo domains are read-only, which is useful behavioral context not captured in the annotations. No contradiction.
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?
The description is two sentences long and front-loaded with the core purpose. Every sentence contributes value: the first states what it does, the second provides usage context and a caution. No wasted words.
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 one-parameter read-only tool, the description covers the key behavioral aspects: return content, usage context, and a permission caveat. An output schema exists, so it need not detail return values. It is complete enough for a correct invocation, missing only deeper parameter semantics already penalized.
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 description coverage is 0%, so the description must compensate. The only parameter, 'domain', is not described beyond the passing phrase 'a domain's rule set'. No examples, valid values, or guidance on how to identify a domain. The description adds essentially no meaning beyond the parameter name itself.
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 uses the specific verb 'Fetch' and clearly identifies the resource ('a domain's rule set') and the output format ('editable YAML'). It also mentions additional outputs (parsed rules and editability), which further clarifies its role. This clearly distinguishes it from siblings like list_rules and put_rules.
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 explicitly states when to use this tool: 'Use this before put_rules to see the current rules'. It also provides an important caveat about built-in demo domains being read-only, giving the agent actionable context for when this tool is appropriate.
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.
Each tool serves a clearly distinct purpose: decide executes decisions, rule management tools (get_rule_source, list_rules, put_rules) each address different aspects of rule viewing/editing, import_policy_rules handles policy-to-rule drafting, and document tools handle knowledge base content. No two tools are easily confused.
All tool names follow a consistent verb_noun snake_case pattern, e.g., list_rules, get_usage, put_rules, import_policy_rules. The single-verb 'decide' fits naturally as the core action. There is no mixing of styles or unpredictable naming.
With 8 tools, the server is well-scoped for its purpose of rule-based decisioning with RAG support. Each tool represents a distinct capability in the workflow—policy ingestion, rule authoring, knowledge base management, decision execution, and usage monitoring—without excess.
The tool set covers the core lifecycle: ingest policy text, import draft rules, publish rules, list rules/source, and execute decisions. Minor gaps exist such as no explicit delete for documents or rules (though put_rules with empty YAML can effectively clear rules), and domain listing is indirect via list_rules. These are workable omissions.