Delimit Review

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

Beyond the annotations' readOnlyHint=false and destructiveHint=false, the description discloses side effects: calls multiple models via ai.multi_review, may write a saved review record, and when pr_url is provided returns a comment body without auto-posting. This materially clarifies what invoking the tool can do.

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 front-loaded with the core purpose, then logically organized into usage, non-usage, sibling contrast, and side effects. Each section adds distinct information without fluff or repetition that wastes tokens.

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 required parameters and an output schema present, the description covers all essential selection and invocation context: what it does, when to use it, when to avoid it, which siblings are alternatives, and what side effects to expect. An agent can confidently choose and call this tool based on the description alone.

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. The description adds extra semantic value for pr_url by explaining the post-as-comment behavior is caller-driven and that the tool returns the comment body rather than auto-posting, which goes beyond the schema's 'GitHub PR URL for linking the review.'

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 'Run a multi-model code review on a diff or file,' naming a specific action, resource, and input. It further distinguishes itself from delimit_audit and delimit_deliberate, making its scope immediately clear.

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 explicitly states 'When to use' and 'When NOT to use,' naming the exact sibling tools that should replace it in other scenarios. The sibling contrast section reinforces the decision boundary with concrete lens/debate vs. single-prompt review distinctions.

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