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

Annotations declare readOnlyHint=false, destructiveHint=false, idempotentHint=false and openWorldHint=true; the description adds substantive context beyond that: the 5120 KB cap, format restriction, aspect-ratio/minimum-dimension requirements per asset type, and the Search-account eligibility/refusal rules. It does not explain what happens on re-upload of the same asset name (duplicate creation) or any permission requirements, which keeps it short of 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?

Front-loaded with the core action, then a clearly separated usage section and an Args section. Every sentence carries non-redundant information, though the aspect-ratio enumeration is dense and slightly long relative to the core call decision.

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 and the description only briefly gestures at return values (resource name, mime_type, width, height), which is acceptable. With three undocumented-in-schema parameters, the description fully compensates on inputs, constraints, and downstream routing, leaving nothing an agent needs to call this tool correctly.

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 description coverage is 0%, so the description carries the full burden and does so: customer_id is 'numbers only, no hyphens', image_source enumerates the three accepted forms (http(s) URL, base64 data URI, local file path) and warns the path form only works when the server shares the filesystem. asset_name is described as the asset's display name. All three parameters gain meaning absent from 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 first sentence names a specific verb and resource — 'Uploads a PNG or JPEG image (max 5120 KB) to the account's asset library' — which is immediately distinguishable from siblings like create_text_asset, create_youtube_video_asset, or create_logo_asset variants. Scope and accepted formats are stated up front, so an agent can select it 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?

The description explicitly routes the agent: use add_assets_to_asset_group for Performance Max, link_asset_to_campaign / link_asset_to_ad_group for Search, and it names the exact asset field types (MARKETING_IMAGE, SQUARE_MARKETING_IMAGE, LOGO, AD_IMAGE, BUSINESS_LOGO) each context accepts. It also states the negative case — marketing image and logo types are refused for Search campaigns — which is genuine when-not guidance.

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