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

Beyond the annotations (which say non-idempotent, non-destructive, closed-world), the description adds crucial traits: the draft is private and not published, external-file/form/server-code pages are refused with file and reason named, and the request_id retry semantics. This is rich context the structured fields do not carry.

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?

Dense but front-loaded with the core action and return value, then the input modes and constraints. Every sentence carries information, though the paragraph could be broken into clearer chunks for scanning.

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 usefully names the return (preview link) and failure modes. For a five-parameter nested-input mutation it is nearly complete, though it could note what happens to the draft afterward or size limits for full 5-level coverage.

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 80% so baseline is 3. The description adds meaning for 'files' (complete static site, relative paths, all assets) and 'business' (starter layout details), plus the request_id duplicate-prevention behavior, going beyond the schema's own notes.

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 uses a specific verb and resource ('Saves a new private website draft'), names the return ('private preview link'), and enumerates the two accepted input modes (files vs business). It is clearly distinguishable from siblings like get_website, list_websites, and update_website.

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?

It states the two mutually exclusive input modes and their content requirements, plus which pages are refused and why. It lacks explicit routing to sibling alternatives (e.g., use update_website to modify an existing draft), so it falls short of 5.

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