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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive), so the description is free to add real value — and it does, by enumerating the four terminal/intermediate return states including previewUrl on success. It stops short of noting what an agent should do on needs_clarification or whether repeated polling is expected.

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?

Two clauses, both front-loaded: purpose first, then the enumerated outcome states. No filler and nothing repeated from the schema verbatim.

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 no output schema, the description correctly takes on the job of describing return states, and does so. It is slightly incomplete for a polling tool — it doesn't say whether states are transient, how often to re-check, or what to do when the result is needs_clarification.

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 buildId description already says 'returned by build_app', which the tool description echoes. Baseline 3 applies: the description adds no format or provenance detail beyond the schema.

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 ('Check the status of a PromptUI build') and anchors it to the producing tool ('started with build_app'). It doesn't distinguish itself from sibling list_builds, which an agent could plausibly confuse with a single-build status lookup.

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?

Naming build_app establishes the natural workflow context (build then poll), which is useful implied guidance. However, there is no explicit statement of when to use this versus list_builds, nor any guidance on polling/when to stop.

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