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

Annotations already establish readOnly/idempotent/non-destructive, and the description adds value beyond them: it says the call is free, that the url form is a public link requiring no login at full size, that bytes are downscaled to ~1024 across, and warns that full-size designs cost hundreds of thousands of tokens and that choosing wrong 'is expensive'. That cost and safety context is not in the 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?

Front-loaded with 'Free.' and the essential routing rule, and every sentence carries a decision-relevant fact. Some phrasing is discursive ('and getting it wrong is expensive', 'not by habit'), which costs a little density but does not obscure the call.

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 no-output-schema read tool, it covers everything an agent needs: required asset_id usage pointer, both output modes with defaults, embedding syntax, resolution behavior, and cost implications. No material gap remains.

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 adds real meaning: it explains the default value and behavioral consequences of `as`, and the embedding format for bytes (data:<mime>;base64,<bytes>) and the cost tradeoff for max_width ('smaller is cheaper') that the schema only implies.

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 (fetch an image asset by its asset_id) and immediately distinguishes the two output forms, which is the real decision the caller faces. An agent can tell this apart from siblings like get_concepts or audit_page 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?

Explicit routing: `as: "url"` is named as the default and usually right, with concrete conditions ('anything you publish with publish_page', 'showing somebody a design'), while `as: "bytes"` is scoped to 'ONLY for a document you are writing in a place that refuses to load pictures from other websites, which includes artifacts'. This is when-to-use and when-not, not inference.

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