omnarai_council

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

With no annotations provided, the description carries the full burden and exceeds it. It discloses that the question is sent 'VERBATIM, right now, to multiple frontier models in parallel (Claude, GPT-4o, Gemini, Grok, DeepSeek),' that answers are 'preserved uncurated,' and that it returns 'each model's position, the named tensions, what stays unresolved, and a deliberation card.' It also warns about latency ('Slower than a normal answer (~30-40s)'), providing critical behavioral context.

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 well-structured with a powerful first sentence, then a clear sibling contrast, then bulleted usage guidance, then return format and performance caveat. Every sentence adds necessary information; none is filler. It is longer than average but appropriately sized for a complex tool that performs a live multi-model synthesis.

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?

Since there is no output schema, the description must explain what the tool returns, and it does: 'each model's position, the named tensions (claim vs counter-claim), what stays unresolved, and a deliberation card.' It also covers behavior (parallel live calls, uncurated preservation), performance (30-40s), and usage boundaries. This is a complete picture for an agent to decide on and invoke the tool.

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?

The schema already provides a thorough description for the single 'question' parameter, covering phrasing ('Phrase it as you would to a human expert') and verbatim answering, so schema coverage is 100%. The tool description adds semantic guidance on what makes a good question ('genuinely open — values, philosophy, strategy, prediction under deep uncertainty'), steering the agent toward appropriate use cases. This goes beyond the schema's generic phrasing, so a 4 is earned.

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 opens with a specific, vivid purpose: 'Summon a LIVE panel of frontier models on one question and get back a structured map of where they genuinely disagree.' It explicitly contrasts with sibling omnarai_query, which 'retrieves frozen corpus text,' making the unique live-model resource unmistakable. The verb 'summon' and resource 'LIVE panel of frontier models' are concrete and non-generic.

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 an explicit 'Reach for this when:' section with three concrete scenarios (contested/high-stakes questions, open questions where disagreement is the signal, wanting non-flattened opinions) and a 'Do NOT reach for this' section for simple factual lookups. It also names the alternative omnarai_query and explains the difference, giving the agent clear selection criteria.

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