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

With no annotations, the description carries the full burden of behavioral disclosure. It reveals a critical nuance: counts are attributions, not deduplicated totals, because creatives/plans can cover multiple countries/platforms. It also notes the 'Return aggregates only' scope. It does not cover output format or error handling, but the key counting behavior that could mislead an agent is clearly explained.

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?

Three sentences, each earning its place: the first states purpose, the second clarifies attribution semantics, and the third gives usage conditions plus the sibling alternative. Information is front-loaded and there is no filler.

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 18-parameter tool with no output schema, the description covers the core purpose, the counting semantics, required filter constraints, and the primary alternative. It does not mention pagination, limits, or the result shape, but those are secondary given that the schema fully documents parameters and no output schema exists. The essential decision-making info for an agent is present.

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 100%, so the baseline is 3. The description adds the grouping dimension (platform and country) and mentions the need for at least one filter, but it does not elaborate on any specific parameter beyond what the schema already documents. The vague 'creative-label filter' does not map cleanly to a schema parameter, adding little value.

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 the verb 'Aggregate' and a specific resource ('ad-plan and creative counts/shares') grouped by 'delivery platform and country'. It explicitly contrasts with get_game_platform_stats for deduplicated totals, which distinguishes it from a key sibling without needing to inspect schemas.

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?

It states exactly when to use the alternative ('Use get_game_platform_stats for single-game/platform deduplicated totals') and enumerates the required conditions for calling this tool: explicit dates (max 180 days) and at least one of the listed filters. This leaves no ambiguity about prerequisite inputs.

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