Ask a question to four frontier AI models that deliberate and produce a synthesis. Ideal for controversial or open-ended queries needing balanced perspectives.
Ask a question to the AI Parliament — 4 frontier models deliberate and a synthesis is generated. Good for controversial or open-ended questions.
| Name | Required | Description | Default |
|---|---|---|---|
| question | Yes | Your question (max 500 chars) |
Changes observed during successful MCP inspections.
v0.2.0Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the full burden of behavioral disclosure. It reveals the deliberation process and synthesis output, which is helpful, but it does not state whether the call is read-only, whether it creates a run, or any potential latency or rate constraints. This is a minimum viable disclosure given the absence of annotations.
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?
One concise sentence that front-loads the main action, then gives the process and a usage hint. No wasted words or redundancy.
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 one-parameter tool without output schema, the description conveys enough to call it correctly: what to ask, what happens, and what will be returned (a synthesis). It omits things like whether the call is synchronous or any cost implications, but the core usage is clear and complete enough for the tool's simplicity.
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 100%, so the baseline is 3. The description adds the idea that the question should be controversial or open-ended, which guides parameter value selection, but it does not add format, examples, or constraints beyond the schema. Only modest additional meaning.
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 states the specific verb and resource: 'Ask a question to the AI Parliament' and explains the behavior ('4 frontier models deliberate and a synthesis is generated'). This clearly differentiates it from siblings like kalei_run_result or kalei_leaderboard, which are about runs or ranking rather than direct questioning.
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?
Offers clear context: 'Good for controversial or open-ended questions.' This implies when to use the tool, though it does not explicitly name alternatives or state when not to use it. That matches the 'clear context, no exclusions' level.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.