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

Annotations cover the safety profile (readOnly, idempotent, non-destructive), and the description adds genuinely new operational facts: 1 credit per call, accepted input encodings, and a 1 MiB inline output ceiling. It stops short of saying what happens when the result exceeds 1 MiB (error vs truncation), which is the one behavioral gap.

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 first three sentences are dense and well front-loaded (capability, cost, I/O contract). However, the description ends on a dangling fragment, 'The converted image', which is an incomplete sentence that wastes space and slightly muddies the return-value statement.

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 correctly carries the return contract: inline file with enumerated MIME types and a size cap. For an 8-parameter tool at 88% schema coverage the essentials are present; only the over-limit behavior and any latency/size tradeoff for resizing are unstated.

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 description coverage is 88%, so the schema already documents nearly every parameter. The description's mention of quality, fit modes, transparency handling and metadata stripping merely names fields that the schema explains in more detail, adding no new semantics.

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 pair (convert and resize) plus the resource (images) and enumerates the supported format set, which is enough to separate it from raster-unrelated siblings like svg_to_png, html_to_image and screenshot without opening any schema.

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?

Usage is implied by the operation itself (you reach for this when you need a different image format or dimensions), and the cost line signals this is a billable server call. But there is no explicit when-to-use/when-not guidance and no pointer to alternatives such as svg_to_png for vector sources.

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