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

Beyond the annotations (readOnlyHint=false, destructiveHint=false, openWorldHint=true), the description discloses the safety-critical behavior an agent most needs: the campaign is always created paused and spends nothing until a separate confirmed enable step. This materially changes how an agent should sequence and communicate the call, and it is not derivable from the annotations or schema.

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 core action, then the enumeration of contents, then the critical paused/confirmation caveat and the dry_run affordance. Dense but every clause carries information; it could be marginally easier to scan if the payload list were itemized rather than run into one sentence.

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 23-parameter, 7-required mutation tool with no output schema, the description covers the conceptual scope, the default behaviors that matter, and the safety flow. The notable gap is that it never says what comes back (e.g. created campaign/ad group IDs) nor that an `account` must be resolvable, which an agent needs in order to chain a follow-up enable call.

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 57%, so the description has real work to do, and it delivers the most important addition: `locations` (a required param with no schema description) accepts either place names like 'Alexandria'/'Riyadh' or geo target IDs. It also clarifies the default location mode as 'people in the location'. It leaves other undocumented parameters (ad_group_name, path1/path2, negative_keywords, account, reason, confirm) to the schema, so it is a partial but valuable compensation.

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 and resource ("Create a Google Ads Search campaign") and then enumerates the full payload it produces: budget, bidding, locations, languages, Search Partners, dates, one ad group with keywords and negatives, one responsive search ad. The "Search" qualifier plus the component list makes it unambiguously distinct from the sibling campaign-creation tools (create_display_campaign, create_pmax_campaign, create_shopping_campaign, create_app_campaign).

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?

Gives concrete operational guidance: the campaign is always created PAUSED, enabling is a separate step requiring user confirmation, and dry_run=true validates without creating anything. It stops short of naming which sibling to use for adjacent tasks (e.g. google_ads_add_keywords for later keyword additions, google_ads_enable_campaign by name), so routing is implied rather than explicit.

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