q_review_start

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

No annotations are provided, so the description carries the full burden and it delivers richly. It discloses that the call returns immediately instead of blocking (async job), gives expected wall-clock timing (1-8min default, 4-15min extended), spells out the empty-diff short-circuit that returns a 'nothing to review' message without running the council, details verbose output behavior (HELD lines, agreement counts), and explains the stance rotation at round 3 for extended mode. This far exceeds baseline behavioral disclosure.

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 long, but every paragraph earns its place for a 12-parameter async background tool. It is front-loaded with purpose and the return contract, then flows logically through the anti-bias gate, target values, scope, execution modes, output verbosity, and timing. The final timing note is a genuine value-add. It could be tightened slightly, but the length is justified by complexity rather than padding.

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 tool of this complexity — 12 params, async behavior, background execution, no annotations, 0% schema coverage — the description is remarkably complete, covering the workflow, the caller's required participation (anti-bias gate), short-circuit behavior, per-parameter semantics, and timing expectations. The output schema exists so return values need no further explanation, and job_id is already surfaced. The only completeness gap is the five undocumented parameters (agents, skip_gh, no_context, host, cwd) that the description leaves to the schema, which is empty.

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 does for the majority. target gets a detailed breakdown of every value ('working', 'pr:N'/URL, 'A..B'/'A...B', 'all', default branch-vs-main), and scope_path, extended, mode, verbose, roles, and gemini_model are each explained. However, five of the twelve parameters (cwd, host, agents, skip_gh, no_context) are not touched in the description and, with zero schema descriptions, remain entirely undocumented — a real gap for a tool where agents and skip_gh likely matter.

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 opening line states a specific verb and resource — "Start a q-review run in the background. Returns {"job_id": str} immediately" — and explains the mechanism (independent agent review then convergence across rounds). This clearly distinguishes a review tool from its siblings q_plan_start, q_brainstorm_start, and q_validate_start, which by naming convention cover different activities. No ambiguity about what this tool does.

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 strong usage context: it is for reviewing real code changes, and it explicitly routes retrieval to a sibling — "Retrieve results by calling `q_await` with the returned job_id" — which orients the agent within the family of q_* tools. It also defines the structural anti-bias gate the caller must pass between start and await. However, it never explicitly states when NOT to use this tool versus q_validate_start or the other review siblings; exclusions are implied rather than stated.

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