Submit opt-in anonymous conversion aggregates with opaque references to report ad network conversions while preventing exposure of raw PII or credentials.
Opt-in anonymous conversion report. Send only opaque references and aggregates, never raw PII or credentials.
| Name | Required | Description | Default |
|---|---|---|---|
| count | No | ||
| value | No | ||
| period | Yes | ||
| currency | No | ||
| node_ref | Yes | ||
| dedupe_key | Yes | ||
| event_type | Yes | ||
| campaign_ref | Yes |
Changes observed during successful MCP inspections.
v0.1.0Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the full behavioral burden, and it does add one genuinely useful constraint: the payload must contain opaque references and aggregates, never raw PII or credentials. However, it never states that this is a write/submission, that dedupe_key implies idempotency or what happens on a duplicate, nor any auth or rate-limit context.
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?
Two short sentences with zero filler, and the identifying phrase is front-loaded. The opening fragment is terse to the point of being syntactically incomplete, but nothing is redundant.
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 8-parameter, 5-required submission tool with no annotations and no output schema, the description is far too thin. An agent cannot learn the expected format of period or event_type, the semantics of dedupe_key, or what a successful call returns or stores.
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% across 8 parameters, so the description must compensate and largely does not. It gestures at "opaque references" and "aggregates", which loosely map to node_ref/campaign_ref and count/value, but period, event_type, currency and especially dedupe_key are left entirely unexplained by both schema and description.
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 identifies the resource as an anonymous conversion report but never states the action (submit/send/record) explicitly, leaving the agent to infer it from "Send only...". It also fails to distinguish this from adjacent siblings such as ads_network_aggregate_publish, ads_attribution_report and ads_network_platform_report, all of which sound like they handle reporting data.
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?
"Opt-in" is the only usage signal, and it describes a property of the feature rather than a condition for selecting this tool. There is no statement of when to call this versus the aggregate-publish or platform-report siblings, and no prerequisites or exclusions are given.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.