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

Annotations say readOnlyHint=false and destructiveHint=false, and the description usefully confirms the side effect (starting the preview) while explaining the meaning of the healthy:false field in the response. With no output schema, that explanation of return-value semantics adds real value. It still omits whether startup is slow or blocking, and how it relates to start_preview.

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?

Two short sentences, zero filler, with the action and the returned-value caveat both front-loaded. Every sentence carries information.

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 single-parameter tool with annotations and no output schema, the description covers the action, the return URL, and the healthy flag. It is still incomplete on the key ambiguities: how this differs from start_preview and what happens on a slow or failed preview start.

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% and there is a single optional project_id already documented in the schema, including the 'or use session from use_project' note. The description adds nothing about the parameter, so the baseline of 3 applies.

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 gives a concrete verb and outcome: start the preview if needed and return the public URL. That is clearer than the name 'get_preview' alone, which suggests a read. However, it never distinguishes itself from the sibling start_preview, so an agent cannot tell from the text which of the two to call.

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?

'Start the preview if needed' implies idempotence and that a prior start_preview call is unnecessary, which is mild guidance. But there is no explicit when-to-use, no exclusion, and no mention of start_preview, get_status, or get_health as alternatives, despite several plausible siblings.

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