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

The annotations already establish that this is a non-read-only, open-world, non-destructive operation. The description adds useful behavioral context beyond those annotations by stating that it returns the extension result and identifier, or a validation/platform error, and that campaign attachment is not part of this call.

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 description is three tight sentences with the core operation front-loaded, followed by return behavior and the important attachment scope. There is little waste and the key routing information is easy to scan.

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 relatively complex create tool with no output schema, the description does well by explaining the return and separation from attachment. However, it does not surface required-field or conditional-parameter expectations, leaving an agent to rely on a partially documented input schema.

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?

The description only says 'using the supplied fields' and does not explain the 11 parameters or their conditional relationships. With only 55% schema description coverage, it does not compensate for undocumented required fields such as occasion, item, category_type, and details_type, though the schema's enums and some optional-field descriptions carry partial meaning.

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 uses a specific verb and resource: 'Create a promotion extension' in the Microsoft Ads asset library. It distinguishes the operation from Google promotion extensions by naming Microsoft Ads, and distinguishes asset creation from campaign attachment by explicitly stating that attaching is a separate operation.

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 clearly indicates that this tool creates an asset and that attaching the extension to a campaign is handled separately, which prevents a common misuse. It does not enumerate when to choose this over the other Microsoft extension creation siblings, but the resource name makes the intended use clear.

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