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

With no annotations, the description carries the full burden and does so thoroughly: it records and enforces no consent, expires after 24 hours and replaces itself with a notice, returns HTML with previewMode: true, makes zero backend calls, never accepts a real appID, and never emits previewMode: false. These are critical behavioral disclosures beyond a generic 'generate' statement.

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 description is long but every sentence is purposeful and front-loaded: the LOOK-ONLY warning comes first, followed by expiration and safety-critical behavior, then the return value, then routing to alternatives. There is no filler or tautology.

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?

For a tool with no annotations and no output schema, the description comprehensively covers purpose, key behavioral constraints, return type, scope limits, and alternative tools. The only gaps are undocumented parameters, which fall under parameter semantics; operationally an agent has enough context to invoke it safely.

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 schema only documents text and design (40% coverage). The description adds that the output is 'styled per the given design/text overrides', clarifying those two parameters and referencing demo.explainConfigKey for valid design keys. However, blocking, globalCookie, and currentLanguage receive no semantic explanation, so the low schema coverage is not fully compensated.

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 opens with 'LOOK-ONLY PREVIEW of the Cookie Compliance banner' and explicitly states 'for showing someone how it would LOOK, never for adding consent management to a site.' It identifies a specific verb, resource, and scope, and distinguishes itself from install.getSnippet by declaring 'NOT AN INSTALL'.

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 description explicitly gives when-to-use ('for showing someone how it would LOOK') and when-not-to-use ('never for adding consent management'), then names the alternatives: install.getSnippet (needs an AppID), help.startSignup, account.* tools (need authenticated connection), and help.explainTokenSetup. Nothing is left to inference.

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