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

Annotations already establish readOnly=false, destructive=false, and idempotent=true; the description is consistent with those and adds beyond them: a 1-credit cost, a 15-minute temporary download link, and an explicit instruction to include the link in the reply. It doesn't describe edge cases or failure behavior, but the added cost/return context is meaningful.

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 description is front-loaded with the core purpose and then adds only decision-relevant details: fit mode, formats, minimum required operation, credit cost, and return-link behavior. Each sentence earns its place, and there is no filler.

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-image transform with rich schema descriptions, this is complete: it covers accepted inputs, what operation is required, cost, and the output delivery mechanism despite no output schema. An agent has what it needs to select parameters and understand the response format.

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 input schema already documents all six parameters with 100% coverage, so the bar is baseline 3. The description adds value by stating the 'at least one of width, height, format or quality' precondition and by revealing that GIF/TIFF are acceptable inputs even though they are not output format options.

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 states a specific action set ('Resize, convert or compress') and resource ('ONE image'), and names the supported conversions and input formats. This clearly differentiates it from sibling PDF, validation, and generation tools such as images_to_pdf or html_to_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?

The description gives clear context for when to call it: transform a single image by resizing, converting, or compressing, with the input formats listed. It does not explicitly name alternative tools or when not to use it, but the 'ONE image' scope and format list provide enough guidance for an agent.

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