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

Goes well beyond the annotations (readOnlyHint=false, destructiveHint=false): it discloses that this only returns a PREVIEW, that unpushed fields are preserved, that the asset ID and performance history survive relinking, that final_url is reachability-checked, and that the preview pins current values against concurrent edits. These are exactly the mutation-behavior facts an agent needs before proposing a change.

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 key fact (PREVIEW) and organized as short, information-dense sentences about scope, partial-update semantics, and conflict behavior. The trailing Google Ads API documentation link is boilerplate that does not help selection and slightly dilutes an otherwise tight definition.

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 an output schema present, the description does not need to explain return values, and it instead covers the risky parts: preview-only execution, partial update semantics, history preservation, and stale-preview detection. Nothing an agent needs to call this safely on a 6-param mutation tool 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 baseline is 3, but the description adds a crucial semantic the schema does not: empty/unset fields mean 'leave unchanged', which disambiguates the many default-"" string parameters. It also reinforces the reachability requirement on final_url beyond the schema's 'must be reachable'.

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?

States a specific verb and resource ('Draft changing a sitelink asset in place') and clarifies it modifies an existing asset rather than creating one, which implicitly separates it from draft_sitelinks. It stops short of naming a sibling explicitly, so the differentiation relies on inference from 'in place' and 'keeps its ID'.

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?

Clearly frames this as the preview half of a two-step preview/apply workflow and warns that a concurrent edit in Google Ads will stop the apply, which tells the agent when the operation is safe. It never names confirm_and_apply or states when to use draft_sitelinks instead of this tool, so the routing remains implied.

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