council_start

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

With no annotations provided, the description carries the full burden of behavioral disclosure. It reveals that seats run concurrently in the background, that the tool returns immediately, that the hat->model mapping is hidden, and that the 'kind' parameter never affects routing—all beyond what the schema or annotations provide.

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 three focused paragraphs: core behavior, optional parameters, and the 'kind' parameter. Every sentence provides value, front-loaded with the primary purpose, and uses formatting (bold, backticks) to enhance readability without waste.

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?

Given the lack of an output schema, the description adequately explains the immediate return value (council_id and blind hat labels) and points to council_poll for retrieving answers. It covers most parameters and important behavioral details, but omits the seat_system_prompt parameter and does not describe potential error conditions or lifecycle management (e.g., council_close).

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 description adds meaningful semantics for four of the five parameters: brief (fanned out to seats), models (optional, default roster), working_dir (defaults to server CWD), and kind (purely descriptive, never affects routing). However, it does not explain 'seat_system_prompt,' leaving that parameter underspecified despite schema description coverage being 0%.

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 'Convene a blind multi-model council on a hard problem,' clearly stating the verb and resource. It then details the exact behavior (fans brief out to one seat per model, runs concurrently, returns immediately) and differentiates itself from siblings by mentioning council_poll and council_reveal, making it distinct from chat and other council tools.

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 gives clear context for when to use the tool ('on a hard problem') and explicitly references council_poll for polling answers and council_reveal for unmasking hat-to-model mappings. It does not explicitly state when not to use it versus chat_start, but the context and sibling references provide sufficiently clear usage guidance.

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