Edit website

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

The description discloses async queueing ('queues the requested changes', 'applied asynchronously'), the return fields ('website URL and ID'), and the mandatory post-call chat behavior. This goes well beyond the basic readOnlyHint=false/destructiveHint=false 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?

Purpose and usage are front-loaded, and the async, return, and chat-response instructions are organized into short paragraphs. The only minor issue is a slight redundancy between 'Do not write code' and 'do not generate code yourself'.

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 2-parameter tool with no output schema, the description covers what the tool does, when to use it, async behavior, return values, success-response requirements, and error-handling behavior. Nothing essential is missing.

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 already documents websiteId and the detailed message object with guidance on describing changes. The description only loosely refers to a 'follow-up message' and 'requested changes', adding no material parameter-level meaning beyond the schema.

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 first sentence names the verb and resource: 'Edit an existing Hostinger Horizons website with a follow-up message.' The qualifier 'existing' and the phrase 'change, extend or fix a website that already exists' clearly distinguish this from creation, cloning, or publishing 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?

'Use this tool when the user wants to change, extend or fix a website that already exists' provides a direct, explicit trigger condition. It does not name sibling alternatives or explicit when-not cases, but the 'already exists' boundary is clear enough for correct selection.

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