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

Beyond the write-implying annotations, the description discloses meaningful behavior: the URL is mirrored into storage and the original can expire, base64 is limited to 8MB decoded, and exactly one source must be supplied. No contradiction with annotations.

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 two dense sentences that front-load the core action and then cover source alternatives, constraints, and use cases. Every clause adds useful information with no filler.

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 five-parameter tool with no output schema, the description covers the key invocation choices and constraints agents need. The role of handle and caption is left to the schema, and the return value is not described, but neither is essential for a safe call.

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?

The schema already covers handle, caption, context, and the two image fields, so the description does not need to repeat them. It adds value by defining the exactly-one constraint, the 8MB decoded limit, and the no-data-prefix base64 convention that are not enforced or fully specified in the schema.

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 clearly states the verb and resource: imports an image into the tenant's asset library. It also distinguishes the accepted source types and typical use cases, so an agent can tell this apart from list_assets, delete_asset, and curate_images.

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 explicit when-to-use guidance for the two input modes: URL when a public URL exists, base64 when the agent holds the image. It also names representative use cases, but it does not explicitly exclude alternatives or mention sibling tools such as curate_images.

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