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

Beyond the annotations (which already declare non-read-only, open-world, idempotent, non-destructive), the description adds billing behavior, the dedupe mechanism ('same pull request head returns the existing review'), the fact that no credentials pass through the tool, and panel composition rules including the first-per-vendor-wins tiebreak. This is exactly the kind of context annotations cannot express.

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 opening sentence front-loads purpose and the follow-up sentence explains the review pipeline before the operational Notes. The pipeline sentence is somewhat elaborate ('ungrounded findings are dropped') but it carries real behavioral information rather than filler; the structure is scannable and nothing is wasted.

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 no output schema, the description still lists what comes back (outcome, agreements, disputes, per-reviewer findings). Auth, private-repo setup, cost, and idempotency are all covered, so an agent has everything needed to call this correctly on first attempt.

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 coverage is 100%, so the baseline is 3, but the description meaningfully extends the `models` parameter: at least two distinct vendors required, tier-gated models need a paid account, duplicates per vendor resolve to the first, and omission falls back to the account default panel. Those are behavioral constraints the schema does not encode.

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 gives a specific verb and resource ('Review a GitHub pull request with Veridu') and explains the differentiating mechanism: finding callers and implementations affected by the change, cross-reviewer gating, and dropping ungrounded findings. It implies but never names the sibling tools (veridu_review_status, verify_change), so routing is inferred rather than explicit.

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?

It states the situation for use (reviewing a PR with dependency context), prerequisites (Veridu account, private repos linked at veridu.io/repos), and cost implications ('counts as one review on that account'). It does not explicitly contrast with the sibling tools get_change, verify_change or veridu_review_status, leaving the agent to infer when those are preferable.

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