[Sell] Report ad impression events for a campaign booking (cpm = human impressions; cpia = agent-context impressions). Batchable; feeds advertiser reporting and billing.
| Name | Required | Description | Default |
|---|---|---|---|
| count | No | Impressions in this batch (default 1). | |
| context | No | ||
| campaignId | Yes | ||
| occurredAt | No | ISO 8601 timestamp, defaults to now. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the burden. It adds useful behavioral context (cpm vs cpia, batchability, feeds billing), but it does not disclose details like idempotency, error handling, or side effects on billing.
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?
A single, information-dense sentence that leads with the verb and resource. Every clause adds value (cpm/cpia distinction, batchability, billing impact), with no unnecessary words.
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 no output schema and no annotations, the description adequately covers purpose but lacks details on response format, context object structure, and potential side effects. It is sufficient for basic selection but not full autonomous invocation.
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 50% (count and occurredAt are described). The description's distinction between cpm and cpia hints at the 'context' parameter's meaning, but it does not explicitly define campaignId or context, leaving some ambiguity.
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 uses a specific verb ('Report') and resource ('ad impression events for a campaign booking'), and clarifies the distinction between cpm and cpia, which differentiates it from sibling reporting tools like report_click and report_conversion.
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 context is clear: this tool is for ad impression events, not clicks or conversions. It also mentions 'Batchable' as a usage capability. However, it does not explicitly exclude alternatives or name when-not-to-use scenarios.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.
Multiple tools have overlapping or misleading purposes: buy_campaign and buy_placement are aliases of create_campaign, list_placement actually creates a placement, and get_attribution/get_campaign both provide campaign stats. The report_* tools are distinct but similarly named, increasing selection risk.
Most tools follow a verb_noun snake_case pattern, but there are notable deviations: buy_campaign/buy_placement use 'buy' instead of 'create', list_placement is a creator not a lister, and simple nouns like 'wallet' and 'whoami' break the convention.
At 31 tools, the server feels heavy. Several tools are redundant aliases (buy_campaign, buy_placement) or could be consolidated (multiple report_* and list_* variants), making the surface unnecessarily large for the ad marketplace domain.
The core lifecycle is covered: campaign/placement creation, delivery, reporting, attribution, refunds, and cashouts. However, there are gaps like no update_campaign, no true list_placements, and no get_placement, leaving some workflows incomplete.
