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

Even with idempotentHint and destructiveHint annotations, the description adds substantial behavioral detail: it creates the app, migrates data, switches the URL, emails the owner, leaves the URL stable, keeps visitor data, and changes nothing on refusal. This exceeds what annotations provide and does not contradict them.

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 core purpose is front-loaded and every sentence adds operational value. There is some redundancy around the URL remaining unchanged and data being preserved, but the overall density remains high and readable.

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?

Covers prerequisites, side effects, check mode, refusal behavior, and the unchanged-URL guarantee, which is enough to call the tool safely. The success return payload is not specified, but there is no output schema, and the refusal response behavior is described.

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?

The schema covers dropId and check with 0% description coverage, so the description must compensate. It clearly explains check=true as a no-op evaluation mode, but it never explicitly defines dropId, leaving that solely to the schema's pattern and the phrase 'one of your drops.'

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 and resource—'GRADUATE one of your drops to tier 4'—and explains the distinguishing outcome: a real backend behind the SAME URL with data carried over. This separates it from sibling operations like publish, release, or rollback without needing to open those tools.

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 clear context: requires an account token and Pro tier, and check=true provides a safe no-op verdict before committing. It does not explicitly name sibling alternatives or when-not-to-use cases, so it stops short of full 5, but usage conditions are clear.

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