Create website subdomain

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

Annotations declare readOnlyHint=false and destructiveHint=false, so it's neither read-only nor destructive. The description adds that this is a create operation, which aligns with the annotations. It does not disclose what happens to the existing website, whether subdomain creation may overwrite existing configurations, or any prerequisites like domain verification. However, given annotations already signal a safe-ish mutation, the description being brief but accurate is adequate; no contradiction.

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 short (two sentences) and front-loads the core action. It avoids repeating the title verbatim and adds one useful detail about optional parameters. It could be more structured (e.g., listing parameter choices), but it earns its place and has no fluff.

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 create tool with 5 parameters (3 required, 2 optional) and no output schema, the description covers the main purpose and optional choices. It doesn't mention what the response will contain (e.g., new subdomain details) or any side effects (e.g., propagation delays). It also doesn't clarify the precedence or mutual exclusivity of directory vs is_using_public_directory, which is a practical gap for correct invocation. Adequate but not fully complete.

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 description coverage is 100%, so the baseline is 3. The description adds meaning to two parameters (directory: 'custom directory ... relative to website root'; is_using_public_directory: 'use the website public directory as the subdomain root') by explaining their purpose in subdomain root selection. However, it does not clarify the relationship between directory and is_using_public_directory (e.g., are they mutually exclusive? What happens if both are set? Which takes precedence?). The schema descriptions are fairly self-explanatory, so the description's extra value is marginal.

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 states the specific action ('Create a new subdomain') and the resource ('selected website'), with a clear verb and object. It distinguishes itself from related subdomain tools like hosting_listWebsiteSubdomainsV1 (listing) and hosting_deleteWebsiteSubdomainV1 (deletion), and from hosted-domain tools like hosting_createWebsiteParkedDomainV1. However, it doesn't explicitly name those siblings, so differentiation is clear from context but not stated.

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 implies when to use this tool: when you need to create a subdomain for an existing website, and mentions optional customization (directory or public directory). It does not provide explicit exclusions or alternatives, such as using hosting_generateAFreeSubdomainV1 for a free subdomain instead. The context signals from sibling names and the description's scope give some guidance, but there is no explicit 'use X instead' guidance.

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