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

Goes well beyond the readOnly/openWorld annotations: the ~1 minute serve delay for new files, the auth caveat that a non-public app is opened without password so member-only content is absent, and the board-edit permission requirement. These are exactly the surprising behaviors an agent needs. Not a 5 only because nothing is said about cost, latency of the capture itself, or failure modes (e.g. what happens if the page never loads).

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-loads what is returned, then usage, then caveats — a sensible ordering with little filler. Some enumeration ('the layout, the text, the empty and error states, and fix what looks wrong') is wordy but arguably instructive rather than redundant.

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?

No output schema exists, yet the description fully specifies the return: two JPEG screenshots at named viewport sizes, captured post-load. Combined with the permission prerequisite and the staleness/auth caveats, an agent has everything needed to call it and interpret results correctly.

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% and the schema itself explains the slug source (list_apps) and the single-vs-multiple workspace resolution rule for organization. The description adds nothing parameter-specific, 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?

States a specific verb and resource plus the exact output: 'returns screenshots of its live address on a phone (390×844) and a desktop (1280×800) as JPEG images.' The visitor-perspective framing and the fixed viewport sizes tell an agent precisely what it gets, distinct from siblings like deploy_app or get_app_source.

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?

Explicitly anchors timing to siblings: 'Use it after deploy_app or edit_app_source and before giving the user the link,' and names the concrete checks to perform (layout, text, empty and error states). The only thing missing is an explicit when-not, but the read-only nature makes that low-risk.

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