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

Annotations already declare destructiveHint=true and openWorldHint=true, so the agent knows this mutates live data. The description adds the important behavioral note that the ad re-enters Google's review process, but 'Goes back to review. Runs directly.' is cryptic and never says whether omitted fields are wiped, whether the ad is paused during review, or what authorization the account parameter needs.

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?

Two tight sentences with the affected fields front-loaded and no filler. The second sentence is terse to the point of ambiguity but earns its place as behavior context.

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 an 11-parameter destructive mutation with no output schema and near-zero schema descriptions, the definition leaves too much unsaid: replace-vs-merge behavior, what 'goes back to review' means for ad delivery, and how dry_run differs. It is not sufficient for an agent to invoke this safely without inspecting the 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?

Schema coverage is only 18%, so the description must carry most of the meaning. It names most creative fields, but never explains the critical replace-vs-merge semantics (are omitted headlines/descriptions cleared?), does not touch ad_id, account, dry_run, or the array limits, and lumps logos/square_images/landscape_images under the vague word 'images'.

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 ('Replace') plus the resource ('responsive display ad') and enumerates the editable fields, so an agent knows exactly which asset this mutates versus google_ads_add_display_ad or google_ads_update_ad. It stops short of naming the sibling tools it should be preferred over, which keeps it off a 5.

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?

'Goes back to review. Runs directly.' gestures at workflow context but never states when to pick this tool over google_ads_update_ad or google_ads_add_display_ad, nor when to prefer the dry_run flag. Usage is implied by the field list rather than stated as guidance.

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