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

Annotations are absent, so the description carries the full burden, and it delivers: it discloses server-side download/store behavior, the exact return shape { filename, sizeBytes, contentType }, SVG rejection criteria (script tags, event handlers, foreignObject, javascript: URLs, external resource references), and the 16 MiB cap with its cause ('Buffered in Worker memory'). This is far richer behavioral disclosure than most mutation tools provide.

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?

Every sentence in the description earns its place: purpose, behavior plus return contract, usage routing, URL constraint, SVG security policy, and size limit. The most decision-critical information is front-loaded, and nothing duplicates what the input schema already documents.

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 tool with no output schema and no annotations, the description covers everything an agent needs to call it correctly: purpose, input constraints, return value shape, downstream chaining, and failure-relevant security and size limits. No critical operational detail is left to inference.

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 the baseline is 3, but the description adds meaningful constraints beyond what the schema states: URLs must not be auth-walled, SVGs must be static/self-contained or they will be rejected, and the returned filename is meant to be passed to add_image_layer. This gives the agent selection semantics and downstream chaining context the schema lacks.

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 ('Upload an image into a project') plus the mechanism ('fetching a public http(s) URL server-side'), making the operation unambiguous. It differentiates from siblings by naming itself as 'the still-image counterpart of upload_clip' and by pointing to find_public_image as the alternative image-pool search flow.

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 guidance: 'Use this when you already have a direct image URL; to search an openly-licensed image pool instead, use find_public_image.' It also states the exclusion criterion ('not an auth-walled page') and explicitly contrasts with upload_clip, so an agent knows exactly when to select this tool over its siblings.

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