render_preview

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

No annotations are provided, so the description carries the full burden of behavioral disclosure. It does convey the read-only nature ('Return') and the two-state behavior (live snapshot vs final preview), but it stays silent on failure modes, whether the call can block or refresh, and how 'newest' is determined. That is adequate but with clear gaps.

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?

One sentence, front-loaded with the action, and every word earns its place. The 'or' clause efficiently captures the two modes.

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?

The presence of an output schema and a single required param lowers the burden, and the description covers the main mode distinction. But with no annotations and a sibling set containing interactive_viewer_preview, render_result, and capture_render_snapshot, the description lacks enough context to prevent selecting the wrong sibling.

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?

The description never says what job_id refers to, how to obtain it, or how it relates to the live/final preview states. With schema_description_coverage at 0%, the description needed to compensate but does not; only the param title 'Job Id' gives any clue.

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?

The description names a specific verb ('Return') and a concrete resource ('newest live snapshot' / 'final preview after completion'), so it clearly identifies a fetch operation tied to render progress. It does not explicitly distinguish itself from siblings such as interactive_viewer_preview or render_result, but the core purpose is unambiguous.

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?

It provides a clear conditional context: use it to get the latest live preview while a render runs, and the final preview after completion. It does not name exclusions or alternative tools, so it falls just short of full routing advice.

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