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

With annotations already declaring readOnlyHint=false and destructiveHint=false, the description adds genuinely new traits: storage is temporary/ephemeral, no server-side rendering occurs, and no design or library asset is mutated. What it does not disclose is retention lifetime or whether a new snapshot supersedes a prior one (idempotentHint=false hints at accumulation but is left unexplained).

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 sentences, zero filler. The audience constraint ('App-only') leads, the core action follows, and the disclaimers close it out.

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?

An output schema exists, so return values need no explanation, and the annotations cover the safety profile. Gaps remain around retention ('temporarily' is unquantified) and the handoff to view_review_snapshot, which is the most likely next call an agent would need.

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 0%, so the description must carry the parameter burden, and it largely doesn't. It characterizes the png argument only indirectly ('a PNG rendered by the edit-result widget') and says nothing about the 4,000,000-character size ceiling or the role of projectId in scoping the snapshot.

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 concrete verb and resource: temporarily stores a PNG rendered by the edit-result widget for visual review. The negative clauses ('does not render on the server or modify a design or library asset') sharpen its scope versus render_screenshots and save_graphics, though it never names the directly paired sibling view_review_snapshot.

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?

The 'App-only' qualifier is useful context on where this call is valid, and the explicit non-goals imply when not to reach for it. But it never states the triggering workflow (e.g. 'call after rendering an edit result, then call view_review_snapshot to retrieve it'), so an agent must infer the sequence.

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