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

Annotations already declare destructiveHint=true and openWorldHint=true, and the description adds useful validation behavior (repeated copy rejected, validation/platform error returned). But it never tells the agent that an update replaces the existing headlines/descriptions wholesale, which is the key destructive consequence the annotations imply.

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?

Three short sentences, front-loaded with the create-vs-update rule, then constraints, then return behavior. The character limits largely repeat the schema, but the paragraph stays tight and wastes little space.

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?

With no output schema, the description still covers the return contract (ad definition or validation/platform error) and the id semantics. It is nearly complete for a 4-param write tool; only the overwrite behavior on update is missing.

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 30-char headline and 90-char description limits restated in the description are already fully documented in the schema. The description adds no syntax or format guidance beyond that, so the baseline of 3 applies.

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 states a specific verb pair (create or update) and resource (Microsoft Ads text ad), and explicitly says an id selects update vs. create. This cleanly separates it from siblings like create_update_google_ads_ad or create_update_image_ad.

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 a clear selection rule: include an id to update, omit it to create. However, it names no alternatives or exclusions (e.g., use archive_ad to retire an ad, or the Google counterpart for other platforms), so the agent is left to infer cross-tool routing.

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