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

Annotations already declare readOnlyHint, idempotentHint, and destructiveHint=false, so the safety profile is covered. The description adds real context beyond them: preview_url is private and never-indexed, public_url is null until publish, and the ownership constraint (non-owned apps answer not found, per schema). It stops short of rate-limit or freshness detail, but that is minor for a read tool.

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?

Purpose is front-loaded in the first clause, followed by the return-value enumeration and then usage. The parentheticals (sandbox bridge, data sources) add flavor that is somewhat expendable, but each sentence still earns its place.

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?

There is no output schema, so the description must carry the return contract, and it does: it enumerates preview_url, public_url, visibility, indexed, and next_step with meaning for each. For a single-param read tool, nothing an agent needs is missing.

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?

Only one parameter and schema coverage is 100%, so the schema already documents app_id fully. The description reinforces ownership semantics but adds no syntax or format beyond the structured field. Baseline 3 is appropriate when the schema does the work.

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+resource (get/open an app's preview URL) and immediately scopes it to 'an app you own.' The preview_url vs public_url distinction plus the explicit mentions of create_app and publish_app let an agent separate this from list_apps, get_app_artifact, and get_app_context.

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?

'Use it to hand a user something to click after create_app, and to check what is still missing before publish_app' gives explicit when-to-use conditions and names the alternative lifecycle calls. Nothing is left to inference about where this fits in the create/publish flow.

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