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

Annotations already establish readOnly, idempotent and non-destructive behavior, and the description adds real context beyond them: the preview reflects the latest saved state, submissions are marked as tests, and no revision-bound browser URL is produced. That last point is valuable scoping behavior the annotations cannot convey.

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?

Three short sentences, front-loaded with what is returned, then the two behavioral constraints. No filler, though the 'No revision-bound browser URL' clause is terse enough to be slightly cryptic without elaboration.

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 does well to name the returned artifacts (standard preview, public and share links), and annotations cover the safety profile. It falls short on the two undocumented input parameters, especially expected_revision, leaving a gap an agent would hit when calling the tool.

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% and the description never explains promotion_id or the sha256-pattern expected_revision, even though the latter is a non-obvious optimistic-concurrency token. The phrase 'No revision-bound browser URL' gestures at revision semantics but does not tell the agent what expected_revision does or when to supply it.

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 states a specific verb (Return) and resource (the standard preview, public and share links) for a saved promotion, so an agent can tell this is a read/preview operation. However, it never differentiates itself from the sibling render_preview, which is the most likely confusion point.

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?

Usage is implied rather than stated: 'Preview always shows the latest saved promotion' and 'No revision-bound browser URL' hint that this is the non-revision-pinned preview path, but no alternative tool is named and no explicit when-to-use condition is given. An agent must infer the choice against render_preview.

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