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

Annotations already declare readOnlyHint=true and destructiveHint=false, so the safety profile is covered structurally. The description adds meaningful extras beyond that: the card-rendering side effect, the do-not-call-during-build constraint, and the semantics of published_at and has_unpublished_changes (including the deleted-file blind spot and legacy null case). It does not, however, describe response shape or pagination, so it stays at a solid 3 rather than maxing out.

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 purpose is front-loaded in the first sentence, and the clauses, while dense, each carry actionable content (address choice, pre-publish check, build-in-progress warning). It is still a long single paragraph that mixes purpose, sequencing, and return-field semantics, so it loses a point for overload rather than waste.

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 read tool with annotations already covering safety, the description supplies everything an agent needs: when to call, when not to call, which address to surface, and what the key status fields mean. Nothing required to call it correctly is missing, even though an output schema exists to carry return details.

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 description coverage is 100% for both parameters, so app_id and context are already documented and the baseline is 3. The description adds no syntax or format detail about either parameter — the fields it explains (site_url, custom_domain, slug) are return values, not inputs.

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 ('Show a website to the user: its screenshot, name and live address') and explicitly distinguishes itself from siblings by naming the unique card-rendering behavior. An agent can tell it apart from get_screenshot, find_app and list_apps without opening any schema.

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 (once after a build/edit has deployed, verified via check_task's deployment_status) and explicit when-not (never while a build is running, because it would show the stale version). It also routes sequencing against siblings publish_app and check_task, including a pre-publish check for work you did not write.

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