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

Goes well beyond the annotations (readOnlyHint=false, idempotent, non-destructive): alpha is flattened onto `background` for jpeg/bmp, metadata (EXIF/GPS/XMP/IPTC) is stripped, refusals and 413s are not charged, images are not logged, url results expire after 24 h, and typical latency is 0.5-2 s. This is exactly the kind the annotations cannot convey.

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 intent and the sibling alternative are front-loaded and nearly every clause carries information. It loses a point because the format list is enumerated twice (once as the goal, once again as the return value) and the second sentence is an unusually long run-on that an agent must parse for limits.

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 10-parameter conversion tool with an output schema, everything an agent needs to call it correctly is present: required `to` values, mutually exclusive input sources, per-format option applicability, size/format limits, cost, and return shape. No meaningful gap remains.

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 baseline is 3, but the description adds real meaning: `background` defaults to white and applies only to jpeg/bmp, `to=ico` yields 16-256 px icon sizes, and quality/progressive/optimize/lossless are tied to specific target formats. Only `auto_orient` and the two input-source parameters are left entirely to the schema.

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 ('Convert an image to PNG, JPEG, WebP, GIF, TIFF, BMP, ICO or AVIF') and distinguishes itself from a sibling by explicitly deferring file-size reduction to image_compress. An agent can identify this tool's job from the first sentence 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?

Names the alternative (image_compress) and the condition that selects it, plus explicit boundaries: accepted input formats, the 40-megapixel refusal, the 15 MB / 50 MP output 413, and the free-tier and pricing terms. When-not and alternative routing are both spelled out.

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