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

Annotations declare destructive/openWorld/non-idempotent/not-readonly, and the description adds substantial context beyond them: it starts an asynchronous internal-agent operation requiring polling, it requires a provisioned site, and source edits may execute in its preview. These are meaningful operational traits the agent cannot get from annotations alone.

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?

Six sentences, front-loaded with the core action and target before moving to async behavior and corrections. Dense but every sentence carries distinct information; only mild tightening would help.

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 compensates by naming the async completion path (poll get_agent_session) and the separate publish step. For a destructive, open-world creation tool with 4 params, this covers the operational prerequisites and lifecycle an agent needs.

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 already 100%, so the baseline is 3. The description adds real value on top: it explains what the instructions content should contain (copy, layout, product references, design requirements) and what to exclude (conversation history, credentials), plus the sessionId continuation semantics. It stops short of detailing the route pattern, which the schema handles.

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+resource with scope ('Create a draft page at one route in an existing site') and clarifies it preserves existing pages. It does not explicitly distinguish itself from the sibling edit_site_page or delete_site_page, which an agent must infer from the verb alone.

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?

Gives explicit when-to-use conditions (provisioned site required), names the follow-up tool for going public (publish_site), and routes corrections back to this same tool with sessionId and unchanged target. The polling alternative get_agent_session is named for the async result. Nothing left to inference.

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