Review the built site

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

No annotations are provided, so the description carries the full burden. It discloses the cost (5 credits, fix 2, free when nothing broken), the return payload (score, summary, changes, changed), and the review workflow. However, it does not explicitly state whether the tool is read-only or mutating (e.g., whether it modifies the plan), which is a notable gap for a tool that returns 'changes made to the plan'.

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 compact and information-dense. Every sentence adds value: what it does, what it returns, and the follow-up workflow. It is front-loaded with the action verb and specific checks, and it avoids redundancy or filler.

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 with one parameter and no output schema, the description explains the return values (score, summary, changes, changed) and the branching workflow. It covers the mode distinction and cost. Missing details include prerequisites (e.g., that a build must exist) and potential error conditions, but these are minor given the tool's simplicity and the clear workflow.

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?

The schema already documents the single parameter `mode` with enum values and descriptions for each mode. The tool description references mode 'fix' but adds no new semantic information beyond the schema. With 100% schema coverage, the description's contribution here is minimal, so a baseline 3 is appropriate.

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 clearly states the tool's purpose: render every built page, inspect for issues, take screenshots, and judge against the brief. It specifies the resource (built site) and the actions, and it naturally distinguishes from siblings like sweipe_ai_build (which builds) and sweipe_status (which likely checks status).

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 explicit workflow instructions: if the returned `changed` is true, call sweipe_ai_build again and then review with mode 'fix'. It also explains the two modes and the credit costs. However, it doesn't explicitly state when to use this tool versus alternatives like sweipe_status or sweipe_list_demos, leaving some inference needed for general usage context.

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