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

Annotations only declare the generic safety profile (not read-only, not idempotent, not destructive, open world). The description goes well beyond that: public-https-only, 100 MB cap, accepted formats, single-use upload URLs that expire in an hour, and aspect inference from images. These are exactly the constraints an agent needs to avoid failed uploads.

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?

Front-loads the core purpose, then walks the three modes in a logical order with no filler sentences. It is a dense single paragraph rather than a structured list, but every sentence carries information the agent needs.

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?

An output schema exists, so return values need no explanation, and the description still covers the non-obvious case where the response contains upload_url/upload_page_url. For a nine-parameter tool with a nested object, an enum, and a write hazard, everything required to call it correctly is present.

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 89%, so the schema already documents most parameters and the baseline is 3. The description adds real meaning on top: the url vs file vs neither decision, that file is populated by ChatGPT, and that aspect is auto-derived when omitted — semantics absent from the schema's enum.

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 (adds an image or video to a brand) and immediately distinguishes itself from read-side siblings like get_media and list_media by describing the three input modes. An agent knows exactly what the tool does 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?

Explicitly explains when to pass url, when to pass file (ChatGPT-attached), and when to pass neither (get an upload link), plus routes the agent to get_media to poll for readiness. It does not explicitly name a sibling alternative for the same task, but the mode-selection guidance is concrete and actionable.

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