consensus-step

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

The description transparently discloses critical behavioral traits: it mutates server loop state, is advisory but mutates on every call, state is ephemeral (lost on server restart), and only dispatch_peers calls external providers. This goes well beyond the annotations (readOnlyHint=false, destructiveHint=false, openWorldHint=true) by adding context about state persistence and external calls.

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 packed with necessary detail, but it is somewhat dense and could benefit from clearer structure (e.g., breaking into sections). It front-loads the overall purpose but the subsequent list of actions and constraints is a bit sprawling. Still, every sentence adds value.

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 complexity (10 parameters, no output schema), the description provides a comprehensive overview of the workflow, state management, and expected replies (text-wrapped JSON envelope). It covers edge cases (sessionId required after init, convergence loop) and parameter constraints per action. However, it does not explain return values in detail.

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 baseline is 3. The description adds meaningful context beyond the schema by grouping parameters by action (e.g., 'init only', 'record_blind only') and explaining semantics like 'blindVerdict: your pre-commit verdict text, written before the panel is revealed'. This helps the agent understand usage constraints.

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 states the tool implements a consensus loop with a specific sequence of actions (init, record_blind, dispatch_peers, submit_adjudication, submit_revision). It explains the role of the host model as arbiter. However, while it distinguishes the tool from abstract siblings like 'consensus' by detailing the step-by-step protocol, it doesn't explicitly contrast with related tools in the sibling list.

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 specifies the required order of actions and that only one action per call is allowed. It implies usage context (client-driven loop) but does not provide explicit guidance on when to use this tool vs alternatives like the simpler 'consensus' tool. No exclusions or when-not-to-use scenarios are mentioned.

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