consensus

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

The description discloses behaviors beyond annotations: it explains the convergence process, default depth, clamping of maxRounds, behavior when synthesizeAlways is true, and configuration options (consensus.arbiter, host mode). There is no contradiction with the readOnlyHint annotation.

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 front-loaded with the main purpose and then provides detailed mode explanations and a note. While somewhat verbose, it packs necessary information for a complex tool. Could be slightly more concise but is well-structured.

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 tool's complexity (8 parameters, no output schema), the description covers core functionality well: two modes, configuration, return values, and alternative usage. It lacks details on error cases and some parameters, but overall it is fairly complete.

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 meaning for maxRounds, synthesizeAlways, and expert parameters, but with only 25% schema description coverage, it does not fully compensate. Parameters like prompt, developerInstructions, reasoningEffort, cwd, and files lack extra explanation beyond the schema.

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 runs a full multi-round consensus loop server-side and returns a converged verdict. It also explains the alternative single synthesis mode, and distinguishes from sibling tools like consensus-step and the /consensus slash command.

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 explicitly provides when to use the tool vs alternatives: it says 'use the /consensus slash command for the transcript-visible host-arbiter loop; this tool is the provider-arbiter path for any host.' It also advises when to use synthesizeAlways for open questions vs plan convergence.

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