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

Goes well beyond the annotations by disclosing that the operation is asynchronous (returns immediately, result via get_site), that it consumes a build credit on paid plans, that it is unavailable on the free plan, and that get_site will report needs_upgrade with an upgradeUrl. This is exactly the cost/async/plan context an agent needs before invoking a mutation.

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?

Front-loads what the tool does and the examples, then the async behavior, then billing. Four sentences all carry information, though the billing detail is slightly dense and could be tightened.

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 an output schema present, return values need not be explained, and the async/polling model plus plan-gating is fully spelled out. Nothing an agent needs in order to call it correctly and interpret the outcome 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%, so the baseline is 3, but the description adds genuine meaning by illustrating what the freeform `request` string should contain (plain-words change instructions) rather than structured fields. `siteId` provenance is already covered in 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?

States a specific verb (changes), resource (an existing website), and clarifies the input modality with three concrete plain-language examples. Clearly distinguishes itself from create_site by scoping to existing sites.

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?

Explicitly routes the agent: the call returns at once and get_site reports the result, so polling behavior is clear. It also states plan gating (paid plans only after first build). It does not explicitly say 'use create_site for new sites', but the 'existing website' scoping makes that inference easy.

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