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

Annotations only declare the generic write/open-world/non-destructive profile; the description goes further by naming the accepted MIME types, the 10 MB ceiling, the two-step upload handshake, and the return contract of a durable email URL capped at 1200px wide. It does not cover failure modes or what happens to existing assets on re-ingest, which keeps it off 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?

Two sentences: the first front-loads the action, formats, size cap, and accepted sources; the second states the return value. Nothing is repeated from the schema and nothing is padded.

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 9-parameter, zero-required tool with nested objects and no output schema, the description should say more about how to choose among the source paths (mutual exclusivity is only implied by 'or') and about the purpose of the unscoped kind/filename/content_type fields. The return value is described sufficiently for an agent to use the result.

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?

With only 22% schema coverage across 9 parameters, the description carries real weight and does the most important job: clarifying that the four image sources are alternative entry points and that image_file is a ChatGPT attachment object. However, it leaves kind, filename, content_type, and the description/alt-text parameter entirely unaddressed, so substantial gaps remain.

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 gives a specific verb and resource ('Store a brand image') and immediately constrains it with supported formats and a 10 MB size limit. It also enumerates the four mutually exclusive input paths (image_file, image_data, image_url, upload then signed_id), so an agent knows exactly what the tool consumes and produces without opening the 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?

It clearly frames the usage context — ingesting a brand image for email delivery, with the 'upload then signed_id' pattern spelled out as a two-step flow and image_file labeled as the ChatGPT attachment path. There are no explicit exclusions or named alternatives, but no sibling tool competes for this job, so the routing signal is strong enough.

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