deliberate_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 it discloses key behaviors: concurrent queries, specific model identities, and that the tool returns raw perspectives for the Host Agent to synthesize rather than a final answer. It does not address cost, latency, or side effects, but the core operational behavior is transparent.

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?

Two sentences with the main action front-loaded and no filler. Each sentence earns its place: what the tool does, how it works (concurrent queries), and what it returns. The size is appropriate for the tool's complexity.

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?

The description covers the main purpose and the shape of the output, and the absence of an output schema means return values need not be detailed. However, for a six-parameter tool with no annotations, it omits when to prefer this over its single-model siblings and gives no caution about cost or latency. Adequate but with clear gaps.

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 coverage is 100%, so the baseline is 3. The description adds some context by mapping the model parameters to their roles (structural blueprint vs adversarial critique), but it does not provide syntax, format, or effort guidance beyond what the schema already documents. The marginal contribution does not raise the score above baseline.

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 a specific verb and resource ('Runs a full multi-model LLM Council deliberation') and details the two sub-queries (Architect for structural blueprint, Contrarian for adversarial critique). It clearly differentiates from the single-perspective sibling tools by emphasizing concurrent execution and the return of both perspectives. No tautology or ambiguity.

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 implies the tool is for getting both perspectives at once, but it never explicitly names alternatives or states when-not-to-use. An agent must infer that consult_architect or consult_contrarian would be the right choice for a single-perspective need. Guidance is left to inference rather than stated.

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