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

Annotations already declare a non-read-only, non-idempotent, non-destructive, open-world write. The description adds genuinely new traits beyond that: uploads persist on the Google account until deleted, a 20 MB size ceiling, and the accepted mime types. It does not discuss auth requirements or failure modes, so it stops short of a 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?

A single dense paragraph that front-loads the operation, then constraints, then the downstream handoff. Every clause carries information; nothing is padding.

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 compensates by describing the return value (the reference id) and how to use it. Combined with source modes, size/type limits, account scoping and asset lifetime, an agent has everything needed to invoke it 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 still adds meaning beyond the schema: it clarifies the url-vs-contentBase64 tradeoff (base64 only for small files), states the 20 MB limit, and ties the email parameter to the chat's account by explaining a reference only works there.

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 states a specific verb (Upload) plus resource (your own JPEG/PNG/WebP image) and target system (a Google Flow account), with source modes spelled out. It is clearly distinguishable from siblings like flow_list_assets or flow_agent_chat, and even names the endpoint POST /assets/{email}.

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?

It gives clear context for the two input modes (public https url vs contentBase64 for small files, 20 MB cap) and explicitly routes the agent downstream: pass the returned id as referenceImage_N to flow_agent_chat, named @referenceImage_N. What is missing is exclusion guidance — it never says when not to use this tool or which alternative to prefer.

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