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

Annotations already declare readOnlyHint=true, openWorldHint=true, and idempotentHint=true, so the safety profile is covered. The description adds useful behavioral detail beyond those annotations: private-address refusal, a 10 MB decoded size cap, base64 output, and the HEIC limitation. It does not describe auth or rate-limit behavior, keeping it at 4 rather than 5.

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?

Five short sentences, each carrying a distinct useful fact, with the core action and supported formats front-loaded. There is no repetition, filler, or buried constraint; the operational limits follow immediately.

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?

Given the annotations, output schema, and 50% schema description coverage, the description covers the essential calling information: input forms, address restriction, size cap, output form, and an important unsupported case. It could still mention the target default and the optional filename/mimeType parameters, but nothing critical for a successful invocation 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 50%. The description reinforces that input is base64 or a public URL and lists the target formats, but those details largely mirror the existing schema descriptions and enum values. It adds the HEIC-not-decoded limitation, yet never mentions filename, mimeType, or the target default, so it only partially compensates for the coverage gap.

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 specific verb (Convert) and resource (image), names the supported output formats, and makes clear it handles base64 or public URLs. An agent can distinguish this from sibling image tools like compress_image, resize_image, and crop_image because the stated purpose is format conversion rather than compression or geometric editing.

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 provides clear operational context: input via base64 or public URL, private addresses refused, 10 MB decoded cap, and HEIC not decoded. It does not explicitly name alternatives for unsupported cases or state when to prefer compress_image or resize_image, so it stops short of full when/when-not/alternative guidance.

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