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

Annotations only declare readOnlyHint=true; the description goes far beyond that, disclosing that nothing is recorded or enforced, that the snippet expires after 24 hours and replaces itself with a notice, that there are zero backend calls, that it never accepts a real appID, and that it never emits previewMode: false. These are exactly the behavioral traits an agent cannot infer from the schema or annotations.

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?

The critical warning (LOOK-ONLY PREVIEW, NOT AN INSTALL) is front-loaded and the expiration caveat follows immediately. It is dense and somewhat long, but nearly every sentence carries distinct, load-bearing information; only the v2 gallery URL is arguably marginal.

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 the work of explaining the return value (ready-to-paste HTML, previewMode: true) and all its safety caveats. The remaining gap is parameter-level: with 5 params at 40% schema coverage and nested objects, the three undocumented flags leave an agent unable to reason about blocking/globalCookie behavior.

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 only 40% and the description adds essentially nothing new: 'styled per the given design/text overrides' merely restates the schema's own 'Partial overrides of huOptions.text.en/design' descriptions. Three of the five parameters (blocking, globalCookie, currentLanguage) are undocumented in both the schema and the description, so the low-coverage gap is not compensated for.

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 and resource ('Generate... preview snippet'), names the exact artifact returned (‘ready-to-paste HTML’ with previewMode: true), and explicitly says what it is NOT ('NOT AN INSTALL', 'never for adding consent management'). It clearly distinguishes itself from install.getSnippet and the demo.* siblings.

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?

Explicitly names the alternatives and the condition that selects each: install.getSnippet (needs an AppID) or help.startSignup for real installation, account.* tools for managing a registered banner, and help.explainTokenSetup for auth. It also gives the when-not ('never for adding consent management to a site').

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