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

Annotations already declare readOnlyHint=false, destructiveHint=false, idempotentHint=false, so the description doesn't need to restate mutation. It adds valuable behavioral context: the asynchronous scan flow, the ~8 second transition, the no-read behavior when description is set, and the free-text nature of kind. It doesn't explicitly state whether repeated uploads overwrite or create duplicates, but the overall behavioral disclosure is strong.

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 description is well-structured with a clear lead sentence, a bulleted two-mode breakdown, and a closing clarification. It is longer than the minimum but every sentence earns its place; the only minor inefficiency is the slightly repetitive phrasing around the two filing modes.

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 tool with no required parameters and an output schema, the description covers the key decision points: how to provide the image, what happens in each mode, how to track completion, and which parameters are conditional. The output schema exists, so return values don't need to be spelled out. Nothing critical is missing for an agent to invoke this correctly.

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. The description adds meaning beyond the schema by explaining the interaction between parameters: description suppresses the read, image_url vs image_base64 are alternatives, and kind/use_when/tags are auto-generated when only the file is sent. It also clarifies that screen_type/device/theme are only relevant for device-framed screenshot masters, which the schema alone doesn't convey.

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 opens with a specific verb and resource ('Upload a brand asset ... into Brand DNA and store it on R2') and immediately distinguishes the two filing modes. It clearly separates this tool from siblings like update_product_screen and list_product_screens by naming the upload-and-store behavior and the polling target.

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 gives explicit when-to-use guidance: it explains the two ways to file an asset, when Gemini reads the picture versus when Siren trusts the words, and tells the agent to poll list_product_screens while scan_status goes scanning → ready. It also clarifies that screen_type/device/theme only matter for device-framed screenshot masters, which prevents misuse.

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