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

Annotations only cover the safety profile (readOnly, idempotent, non-destructive); the description adds substantial context beyond that: the call is free, the url form is public with no login, the bytes form is downscaled to ~1024 across, and full-size fetches would cost several hundred thousand tokens. The embedding syntax data:<mime>;base64,<bytes> is also disclosed.

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 decision that matters most (url vs bytes) is front-loaded and the cost/context warnings are tight and purposeful. It is slightly long and repeats the `as` semantics already in the schema, but no sentence is filler for a tool with this much footgun potential.

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 present, the description carries the burden of describing returns and does so precisely: a public link for url mode, a base64 payload for bytes mode, with sizing behavior. An agent has everything needed to call it correctly and 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?

Schema coverage is 100%, so the baseline is 3, but the description goes further: it marks `url` as the DEFAULT AND USUALLY RIGHT, warns that the choice is expensive to get wrong, and explains why max_width defaults to 1024. It duplicates rather than contradicts the schema's enum documentation, adding rationale the schema lacks.

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+resource (retrieve a stored picture by asset_id) and clarifies that designs, page captures and logos all carry an asset_id. It is unambiguous about what comes back (a link or the image bytes), but it never names or contrasts against siblings such as fetch or export_page, so it falls short of full sibling differentiation.

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 explicitly routes between the two modes: `as: "url"` is the default and correct choice for anything published with publish_page or shown to someone, while `as: "bytes"` is reserved for documents that cannot load external images (artifacts). Both the when and the when-not are stated, plus a caution that asking for bytes by habit is wrong.

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