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

With no annotations, the description carries the burden, and it does disclose the response shape (pattern, confidence, tradeoff matrix, examples), which is genuinely useful. It omits other behavioral facts of consequence: that 'context' accepts a relative file path the tool presumably reads from disk, and any indication of latency or cost (the schema hints at a 'quick' low-latency mode the description never mentions).

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 purpose and followed by the return contract; every clause earns its place and 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?

For a five-parameter consult tool with no annotations and no output schema, the description covers purpose and return values well enough to call it correctly. The remaining gaps - sibling differentiation and the file-reading behavior of the context parameter - are real but secondary.

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 all five parameters are already documented in the schema, making 3 the baseline. The description adds no parameter meaning at all - it never mentions focus, quick, context, or the question/query alias relationship, so it neither compensates for nor improves on 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?

Specific verb and resource: 'Consult the multi-model architecture council for targeted design advice', plus an explicit statement of what comes back (pattern, confidence, tradeoff matrix, examples). It does not differentiate itself from siblings jury_plan and jury_review, so an agent cannot tell from this text alone which of the three to pick.

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 phrase 'targeted design advice' implies a design-time consult, but there is no explicit when-to-use, when-not-to-use, or named alternative among jury_plan and jury_review. The agent must infer the boundary from tool names alone.

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

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

No annotations are supplied, so the description carries the full disclosure burden. It says what the deliberation yields, which is useful, but it never warns that a multi-model jury call is likely slow or expensive, that results may be cached, or what happens on timeout. The async ticket workflow is only described in the schema, not in the description.

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 definition is two tight sentences with the action front-loaded and the outputs enumerated immediately afterwards. No filler or repetition appears, though the output list could be trimmed slightly.

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?

Not penalized for the missing output schema, specifically because the description enumerates the return artifacts, which is what an output schema would have provided. No output schema exists and no annotations exist, and the description substitutes effectively by naming the four deliverables. It could go further by explaining the async follow-up path, but it is adequate for a four-parameter deliberation tool.

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%, including the nested options object and its three flags, so the schema already defines every parameter. The description adds nothing about how 'task' should be phrased or how context_files or async_mode change the outcome, so the baseline of 3 holds.

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 names a specific verb ('Deliberate') and a specific resource ('an architectural implementation plan') and then lists the four artifacts produced: readiness score, risks, modifications, and a file execution plan. That is far more concrete than a tautology. It does not, however, separate this tool from its siblings jury_review and jury_ask, so an agent must guess which one to call when it has a plan.

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 implies usage ('an architectural implementation plan') but never states when this tool should be used instead of jury_review or jury_ask, nor does it give prerequisites, exclusions, or cost or latency warnings. With two close siblings available, the missing comparison logic is a real gap.

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

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.