Pinpoint click ID loss causes such as Safari restrictions, cross-domain redirects, or missing cookies to resolve attribution gaps.
Diagnose common click ID loss boundaries.
| Name | Required | Description | Default |
|---|---|---|---|
| safari | No | ||
| crossDomain | No | ||
| landingQuery | No | ||
| cookieMissing | No | ||
| redirectDroppedQuery | No |
Changes observed during successful MCP inspections.
v0.2.0Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the full burden of behavioral disclosure. 'Diagnose' implies a read-only analysis, but this is not explicit, and there is no mention of side effects, required permissions, or what the tool returns. The description is too sparse to be transparent about behavior.
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 a single short sentence, which is concise, but it is so under-specified that it fails to earn its place. It provides almost no actionable information, so this is under-specification rather than good conciseness.
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 a 5-parameter tool with a nested object and no output schema or annotations, the description is extremely incomplete. It explains neither the parameters' roles nor the expected result, leaving an agent unable to call the tool effectively.
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% – the description mentions none of the five parameters, including the nested 'landingQuery' object. The schema itself only provides names and types, not meaning, and the description does nothing to compensate. An agent has no idea what 'safari', 'crossDomain', etc. mean for the diagnostic.
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 verb ('diagnose') and a resource ('click ID loss boundaries'), which is not a tautology, but 'boundaries' is vague and doesn't clarify what specific diagnostics are performed. It doesn't distinguish from siblings like 'detect_attribution_gaps' or 'validate_attribution_pipeline'.
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?
No usage guidance is provided. There is no mention of when to use this tool versus alternatives, no prerequisites, and no context about the diagnostic workflow. The description gives no indication of when this tool is appropriate.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.