jury_review

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

No annotations are supplied, so the description bears the full disclosure burden. It does well on outputs — blind ballots, adversarial cross-examination, decoupled arbitration, findings, POSIX diff patches, SARIF v2.1.0 diagnostics — which tells the agent this is a heavy multi-model deliberation that returns patches and diagnostics, not just prose. It omits cost/latency expectations for a multi-model panel, whether anything is written to disk or the repo, and what failure modes look like.

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?

Two sentences, front-loaded with the core action and followed by the mechanism and outputs. Dense jargon ('decoupled arbitration', 'OASIS SARIF v2.1.0') but each clause carries information; nothing is padded.

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?

With five optional parameters, no output schema, and no annotations, the description covers the important bases: what it reviews, the deliberation model, and the shape of the return (findings, patches, SARIF). What is missing is operational context — cost, runtime, and whether it mutates anything — which matters for a multi-model panel.

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 100%, so every parameter (diff, focus, branch, staged, strict) is already documented in the schema, including the enum values and defaults. The description adds no parameter-level meaning beyond the schema, so the baseline 3 applies.

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 opens with a specific verb+resource: 'Review code changes or git diffs with the multi-model jury panel.' That is unambiguous and implicitly separates it from jury_plan (planning) and jury_ask (questioning), though it never names those siblings or states the distinction explicitly.

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?

There is no explicit when-to-use or when-not-to-use guidance. The closest thing is 'Review code changes or git diffs', which implies the input domain but says nothing about choosing this over jury_ask for a question or jury_plan for planning, nor about prerequisites such as needing a git repo when 'diff' is omitted.

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