wafle_ads_generate_report_monthly

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

Annotations already declare readOnlyHint=true and idempotentHint=true, and the description fully aligns with these. It adds substantial behavioral context beyond the annotations by detailing the return payload (spend, revenue, profit, ROAS, winning/losing campaigns, recommendations array), the underlying data source, and the month-aware aggregation layer. This is rich, non-redundant 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 two sentences of core functionality plus one sentence of usage guidance and backend context. Each sentence earns its place; it is informative without bloat. The warning about not pasting raw JSON is valuable and concisely phrased.

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 no output schema, the description takes on the burden of explaining return values—it lists all expected fields. It also gives practical usage instructions for the narrative generation. For a report-generation tool with two well-documented parameters, this is complete and possibly exemplary.

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%: both 'slug' and 'month' are explained with examples in the input schema. The description adds little beyond that, but the schema already carries the full weight. Baseline 3 is appropriate because no compensation is needed.

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 opens with 'Generate a structured monthly ads report for a store' and enumerates the exact metrics returned (total spend, revenue, profit, blended ROAS, top 5 winning campaigns, bottom 5 losing campaigns, recommendations). This clearly distinguishes it from sibling tools like wafle_ads_performance_summary or wafle_ads_compare_periods, which target different reporting needs.

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 explains that this is 'Designed as the input for Claude to author the executive narrative' and explicitly instructs not to paste raw JSON, instead rewriting into prose with recommendations as bullet points. It provides clear context for when this tool's output is appropriate, though it doesn't explicitly name alternative tools for different report types.

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