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

Annotations already signal non-readOnly, open-world, non-idempotent, non-destructive, so the bar is lower. The description adds critical behavioral context: expiration in 24 hours, password protection genuinely protects, form Send is mock, claim ownership does not activate features, URL is randomized, no stored submissions/contacts/analytics. This is exactly the kind of context that prevents an agent from making false assumptions about a generator/preview tool.

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 a single dense paragraph with multiple distinct clauses; it is not minimal, but it earns each sentence by adding operational rules. The most important behavioral trait (expiration, anonymous) is front-loaded. It could be split into separate behavior and session-tracking sections for readability, but it remains concise and scannable enough for an agent.

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 do not need to be described. The description fully covers the tool's scoped behavior, limitations, session-tracking requirement, and user-communication rules. For a complex lifecycle tool with open-world and idempotency annotations, this is complete and leaves no obvious procedural gap.

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 100% and most parameters already have descriptive labels and enums. The description adds practical parameter-level meaning by explaining the generated password, never-ask-for-password rule, and the form preset behavior that maps to form_preset. It does not redundantly recite the schema, and it enriches the semantic context.

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 a specific verb and resource: 'Create one anonymous website preview that expires in 24 hours.' It also enumerates functional boundaries (public/password access, one built-in form) and clarifies the intended user-facing outputs. This strongly distinguishes it from siblings like website_preview_update and bucket_publish_preview.

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 gives explicit when-to-use guidance, including the session-level rule about tracking distinct ready preview IDs and the messaging to surface on second creation. It also states what the agent must never ask for (link name, password) and explicitly explains that Send is a mock and claimed previews require republishing. This goes beyond a vague 'when to use' and provides direct operational guardrails.

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