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

Annotations already cover the safety profile (readOnlyHint, destructiveHint=false, openWorldHint=false), so the bar is lower, yet the description still adds real context: it requires an API key with read scope, preview URLs expire after an hour, and identical-byte uploads dedupe. It stops short of describing pagination behavior beyond the limit parameter.

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?

Two dense sentences, zero filler. The resource, sort order and returned fields are front-loaded before the usage and auth notes.

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 enumerates the returned fields itself, and it also covers auth requirements and the error-driven workflow (LIBRARY_IMAGE_LIMIT -> delete_upload). Nothing an agent needs to call it correctly 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% and the single limit parameter is documented with default/min/max, so baseline is 3. The description adds ordering semantics ('newest first'), which tells the agent what the limit actually slices, a modest but genuine addition.

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 ('List the user's Uploads library') and immediately enumerates the returned fields and sort order ('newest first: id, upload:<id> ref, name, pixel size, bytes and an hour-long preview url'). An agent can distinguish this from list_designs/list_decals/search_content 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?

Gives explicit when-to-use conditions and names the related tools: reuse an already-uploaded image (noting identical bytes dedupe anyway) or pick a target for delete_upload when upload_image returns LIBRARY_IMAGE_LIMIT. The alternative-tool routing is concrete rather than implied.

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