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

Far beyond the annotations, it discloses atomic relinking of campaign/account links but explicitly NOT ad-group links, that the old asset remains unlinked in the account, that the new asset re-enters policy review, and the specific failure modes error=relink_failed and error=empty_final_url. This is exactly the side-effect detail an agent needs before a destructive mutation.

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 most consequential fact (in-place URL vs. new asset) and every sentence carries execution-relevant information. Dense parenthetical error codes make it slightly harder to scan, and the workspace note is appended without a transition.

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 destructive, high-complexity mutation with 6 params and no schema descriptions, it covers side effects, link-scope asymmetry, error contracts, and the follow-up use of new_asset_id. An output schema exists, so return-value explanation is not required and the mention of new_asset_id in the response is a bonus.

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 must carry the load, and it does: final_url replaces all prior URLs, an empty value is rejected while omission preserves the current one, and the text/description params are effectively immutable and trigger new-asset creation. Only asset_id itself is left unexplained, which is a minor gap given its obvious role as the target.

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?

Opens with a specific verb+resource ("Sitelink ändern") and immediately clarifies that this updates the final URL in place while text changes spawn a new asset, which implicitly separates it from ads_create_sitelink and ads_link_asset. It stops short of naming those siblings explicitly, so an agent must infer the boundary.

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 text makes clear what invoking this tool does in each case (URL change = in-place, text change = new asset that must be used thereafter), which strongly implies when it is the right call. However, it never states when NOT to use it or points to a concrete alternative such as ads_create_sitelink or ads_unlink_asset.

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