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

Annotations only declare readOnlyHint=false, idempotentHint=false, destructiveHint=false; the description adds the genuinely non-obvious behavioral fact that the write is inert until a separate link call is made. That is the key side-effect disclosure an agent needs. It omits permission/scope requirements and error/validation behavior, and still states a return value despite an output schema existing.

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 behavioral constraint is front-loaded in the second sentence, and the Args block is dense with real constraints rather than filler. The one disposable line is 'Price assets showcase your products or services with their prices,' which is mildly redundant, but overall length is justified by the zero-coverage schema.

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 five-parameter creation tool with a bare schema and an existing output schema, the definition covers everything needed to call it correctly: required fields, enum values, nested offering structure, size limits, defaults, and the two-step link requirement. Return-value documentation is redundant but harmless.

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 0% — price_type has no enum, and price_offerings is only typed as an array of string-valued objects — so the description carries the entire burden. It supplies the full price_type enumeration, the 3–8 offering count constraint, per-field 25-character limits, the micros currency conversion example (9990000 = 9.99), and the unit/qualifier enumerations, which the schema would otherwise leave ambiguous.

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 opens with a specific verb+resource ('Creates a price asset') and immediately scopes it ('can be linked to campaigns or ad groups'), which separates it from the many sibling create_*_asset tools. The added sentence explaining what a price asset is (products/services with prices) reinforces the resource identity rather than restating the name.

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 gives clear operational context that creation alone changes no ad and that the asset only appears once linked via link_asset_to_campaign, link_asset_to_ad_group, or link_assets_to_customer — naming the concrete follow-up siblings. It does not, however, say when to prefer a price asset over create_promotion_asset or create_sitelink_asset for a given marketing goal, so no explicit exclusion guidance.

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