consensus

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

With no annotations, the description carries the full burden and does disclose meaningful behavior: parallel isolated worktrees, a merge-and-verify step, and an asynchronous return contract (group id consumed by wait). It does not state cost implications despite a max_usd parameter, what happens when engines disagree or fail, or whether worktrees are cleaned up afterward.

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?

A single dense sentence with the core workflow front-loaded and the return contract appended where the agent will look for it. No filler, though the telegraphic phrasing trades some clarity for brevity.

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?

For a 6-parameter async orchestration tool with no annotations and no output schema, the description covers the execution model and the follow-up call, which is the essential spine. It still leaves repo, budget limits, failure semantics, and result retrieval to inference, so it is adequate but not 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?

Schema description coverage is 0%, so the description must compensate and it only partially does. It gives meaning to prompt (the shared task), engines (count constrained to 2-4), isolation (worktrees), and verify_cmd (verification step), but leaves repo and max_usd entirely unexplained.

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?

States a specific multi-step action: 2-4 engines solve the prompt independently in isolated worktrees, then a merge job picks the best result with verification and invariant checks. That is a distinct verb-and-resource profile an agent can separate from single-engine siblings like start or map_reduce, though the jargon ('blind', 'invariants') is compressed enough to require a second read.

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?

Usage is only implied: the trailing 'Returns a group id for wait()' tells the agent this is an async launch that must be followed by wait, which is genuinely useful routing information. However, there is no explicit statement of when to choose consensus over start_many, map_reduce, or plan, and no exclusions or preconditions are given.

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