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

Annotations only cover the safety profile (readOnly, non-destructive, closed-world); the description goes well beyond by disclosing the rendering backend (Xodia's headless browser), a monthly allowance, the returned console errors, and two distinct failure modes with prescribed agent behavior. This is exactly the operational 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?

Front-loaded with the core action and return value, then the routing/retry rules. It is dense but nearly every clause carries operational weight; the error-handling run-on is slightly terse in phrasing ('ask the user to look in Xodia and check with run_check and get_logs instead') but not wasteful.

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 four params, no output schema, and safety already covered by annotations, the definition supplies the missing dimensions: what comes back (image + console errors), quota constraints, and failure-mode handling. An agent can invoke and recover from this tool without further discovery.

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 75% and full_page already carries a detailed warning about scroll-reveal sections rendering faded/hidden plus the anchor workaround. The description adds only a passing hint that mobile sizing is possible ('at mobile size too'), leaving the viewport enum values unexplained in the prose; 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?

States a specific verb and resource — 'Renders a page of the preview in a real browser' — and names the return payload (image plus console errors). It is clearly separable from list_pages/get_project style siblings and explicitly points at run_check and get_logs as the fallback path.

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?

Gives explicit when-to-use ('check your work visually, at mobile size too') and when-to-stop rules: if it reports screenshots unavailable or that the project must be open in Xodia, do not call again in this task and instead ask the user / use run_check and get_logs. It also handles the transient case: 'headless_busy means try once more in about 30 seconds.'

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