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

Annotations already declare readOnlyHint=false and destructiveHint=false, so the bar is lower, but the description still adds real behavioral context beyond them: creating the asset mutates nothing on its own and takes effect only once linked to an asset group or used as a campaign's business name. It does not discuss duplicate creation or permissions, though idempotentHint=false is already surfaced in 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 the core action and consequence, then parameter detail, then return value; each paragraph serves a distinct purpose. The Returns section is largely redundant because an output schema is supplied, which is the only real waste.

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 simple two-parameter mutation with annotations and an output schema, this covers what it does, when it takes effect, parameter formats, and the follow-up calls. Missing only edge cases such as duplicate assets and customer-access prerequisites, which are comparatively minor here.

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%, so the description carries the full burden and does substantial work: customer_id is constrained to numbers with no hyphens, and text gets concrete length limits per asset class (30/90/90). It does not explain how the system determines which asset class applies, which would have been the one remaining ambiguity for a two-param tool.

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?

Specific verb+resource: 'Creates a text asset for use in Performance Max asset groups.' It immediately separates this tool from the many sibling create_*_asset tools (image, call, sitelink, promotion) by naming the asset type, and adds the scope 'Performance Max asset groups.' An agent can pick this tool over create_image_asset without opening a 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?

It gives clear when-to-use guidance ('Use this to create headline, description, and long headline assets that can be linked to asset groups') and explains the downstream step by naming the siblings to call next (create_asset_group, add_assets_to_asset_group). It stops short of an explicit exclusion, e.g. 'for image/video/call assets use create_image_asset instead,' so the negative routing is left implicit.

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