google_ads_campaigns_diagnose

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

With no annotations provided, the description carries the full burden of behavioral disclosure. It explicitly states 'Read-only — does not change anything,' which is a clear safety guarantee. It further describes the return behavior: an ordered list of issues drawn from specific status fields, with examples of issue types and the format of each item (plain-language description and remediation hint). This provides meaningful transparency about both side effects and output semantics, though it does not discuss error handling or rate limits. Given the absence of annotations, this is a solid disclosure.

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?

The description is three sentences long and each sentence earns its place: the first states the purpose and output, the second guarantees read-only behavior, and the third gives usage guidance. It is front-loaded with the core purpose, includes concrete examples, and contains zero filler or redundancy. This is a model of concise yet informative writing.

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?

Given that this is a diagnostic tool with no output schema, the description provides a remarkably complete picture: what it does, what it returns (ordered issues with descriptions and hints), the data sources (serving_status, primary_status, primary_status_reasons), safety (read-only), and usage context (before raw reports). It does not mention error conditions or ordering criteria explicitly, but for a single-campaign diagnostic with no output schema, the description is nearly sufficient. The only minor gap is the lack of explicit alternative tool references, but this is covered under usage guidelines.

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 description coverage is 100%, with both campaign_id and customer_id having explicit descriptions in the schema. The description itself does not add any parameter-specific details beyond the schema—it refers to 'a campaign' but does not elaborate on the customer_id fallback behavior, which is already covered by the schema. Since the schema handles the parameter semantics, this is a baseline 3 for a high-coverage scenario.

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 clearly states the tool's function: 'Explains why a campaign is not serving or is under-delivering.' It goes beyond a vague verb by specifying the resource type (campaign) and the specific diagnostic angle (serving/under-delivery), and it distinguishes itself from raw reporting tools by framing its output as an ordered list of actionable issues. This is a specific verb+resource+scope, strongly differentiated from siblings like google_ads_campaigns_get or google_ads_performance_report.

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 description gives explicit when-to-use guidance: 'Use this before pulling raw performance reports; it narrows the problem space.' This establishes a clear context and prioritization relative to performance reporting. It does not explicitly name alternative diagnostic tools (e.g., google_ads_health_check_all) or give when-not-to-use scenarios, but the provided context is sufficiently actionable. This fits 'clear context, no exclusions' rather than a full alternative analysis.

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