Read stored content metrics with captured_at timestamps. Missing metrics are unknown, not zero; does not trigger paid refreshes. For saved X and channel reports use get_report_capabilities and get_channel_report; for fresh reports use request_channel_report.
| Name | Required | Description | Default |
|---|---|---|---|
| limit | No | ||
| cursor | No | ||
| brandId | Yes |
| Name | Required | Description | Default |
|---|---|---|---|
| data | Yes | ||
| source | Yes | ||
| coverage | Yes | ||
| nextCursor | Yes | ||
| freshnessField | Yes |
Changes observed during successful MCP inspections.
Input schema / additionalPropertiesAdded value: +falseDoes the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnly, idempotent, non-destructive, closed-world. Beyond that, the description adds two genuinely behavioral facts: missing metrics are unknown rather than zero, and the call does not trigger paid refreshes. These go past the safety profile and affect how an agent interprets results and whether it should worry about cost.
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, no filler, and the core capability plus the data-semantics caveat are front-loaded before the routing guidance. Every clause carries information an agent needs.
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?
An output schema exists, so return values need no explanation, and the annotations plus the description cover safety, cost, and staleness adequately. The remaining gap is pagination/limiting behavior implied by the cursor and limit parameters, which is unaddressed anywhere.
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% and the description never mentions brandId, limit, or cursor. Pagination semantics (cursor) and result-count bounding (limit) are left entirely unexplained in both the schema and the description, so the description fails to compensate for the coverage gap.
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?
States a specific verb+resource combination: reading stored content metrics with captured_at timestamps. It also distinguishes itself from near-neighbors in the same family (get_analytics_summary, get_channel_report, request_channel_report), so an agent can select it without opening a schema.
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?
Explicitly routes the agent: saved X and channel reports go to get_report_capabilities / get_channel_report, fresh reports go to request_channel_report. This is a clear when-to-use-this vs when-to-use-alternatives statement, which is exactly what usage guidance should do.
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.