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

Annotations cover the safety profile (readOnlyHint false, idempotentHint false, destructiveHint false, openWorldHint true), and the description adds substantial context beyond them: flat 4-credit cost, ~45 s return window, 6-15 minute full budget, the 'running' state and polling cadence, and the 60 s client-abandonment risk that loses the taskId.

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 it does and the cost, then layers the polling/latency guidance. No sentence is filler; each one carries an operational fact an agent needs.

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 still covers the return value (upscaled image URL, or a taskId when running), the failure/latency mode, and the follow-up tool. Nothing needed to invoke and follow through on this job 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 schema already documents all four parameters and the enum; the baseline would be 3. The description adds value the schema lacks — the ~10 s polling interval and the exact get_job(taskId, kind) call to make — justifying a step above baseline.

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 ('Upscales a source image 2x or 4x') and the required inputs, cleanly distinguishing it from siblings like aetherwave_upscale_video, aetherwave_edit_image, and aetherwave_reframe_image.

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 operational routing: default behavior returns within ~45 s, poll aetherwave_get_job with the returned taskId/kind every ~10 s while state is 'running', use wait:true only if the client tolerates >60 s calls, and async:true to skip polling entirely. When-to-use conditions are spelled out rather than implied.

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