consensus-step

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

The description contradicts annotations: readOnlyHint is true, but the tool initiates sessions and submits verdicts (writing state). The description mentions 'Advisory.' at the end, which is ambiguous and does not resolve the 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 a single dense sentence that front-loads the purpose but is difficult to scan. It covers many details but would benefit from being broken into multiple sentences or bullet points.

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 explains the workflow but lacks output schema information, error states, or return values. For a complex multi-step tool with 10 parameters, it is incomplete.

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, but it only loosely references parameters like 'blindVerdict' and 'verdict' within the action context. It does not explain the role of 'expert', 'prompt', 'decisions', or other parameters.

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 clearly identifies the tool as a client-driven consensus loop with specific actions (init, record_blind, etc.), making the resource and verb clear. It distinguishes from siblings like 'consensus' by emphasizing step-by-step arbitration.

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 explicit context for when to use this tool: as the host model arbiter in a consensus loop. It outlines the sequence of actions, but does not explicitly mention when not to use it or provide alternatives.

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