ads_monitor_account

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

With no annotations available, the description carries the full burden of behavioral disclosure, and it does this well: it reveals that the tool aggregates multiple diagnostic categories (policy, budget, pause anomalies, optimization score) into a synthesized overview rather than returning raw data. The main gaps are that it never explicitly states it is read-only/side-effect-free, and it doesn't say what happens when the optional customer_id is omitted.

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 tightly written and front-loaded: the opening sentence states the purpose, the four bullets are scannable and each adds distinct information, and the usage directive and argument note each earn their place. No filler or repetition of schema content.

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 simple one-parameter tool with an output schema present, the description covers the core needs: what it checks, what it surfaces, when to run it, and the argument format. Remaining gaps are minor — no explicit read-only confirmation, no behavior when customer_id is not supplied, and no differentiation from the closely-adjacent ads_list_recommendations sibling. The output schema relieves it of documenting return values.

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 0%, so the description must compensate — and it does: 'customer_id: 10-digit account id' adds the format constraint (10-digit) and semantic meaning (account id) that the bare string/null schema lacks. It could go further by explaining that the parameter is optional and what behavior results from omitting it, but for a single-parameter tool the compensation is adequate.

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 states a specific purpose (health/status monitor) with a concrete verb ('surfaces issues') and a precise resource (account health). The four bullet points define exactly what it detects — disapproved/limited ads, budget-limited campaigns, paused campaigns that recently spent, and optimization score — which clearly distinguishes it from performance-report siblings like ads_campaign_performance or ads_keyword_performance. The 'quick what's wrong / what to fix overview' framing further pins down its role.

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 an explicit usage instruction: 'Run this for a quick what's wrong / what to fix overview.' This provides clear context for when an agent should invoke it. However, it does not name alternatives or state when NOT to use it — e.g., it doesn't contrast with ads_list_recommendations or ads_campaign_performance for deeper per-metric analysis.

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