Headline KPIs for a site: visits, visitors, pageviews, outbound clicks, bots, CTR, bounce rate, session duration. Defaults to the full retained history.
| Name | Required | Description | Default |
|---|---|---|---|
| to | No | YYYY-MM-DD | |
| days | No | Window in days (omit for full history) | |
| from | No | YYYY-MM-DD | |
| site | Yes |
Changes observed during successful MCP inspections. Dates show when Glama detected each change.
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries the behavioral disclosure burden. It usefully notes that it defaults to the full retained history, but it does not describe the output shape, date-range interaction semantics, or the read-only nature beyond what the name implies.
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 two short sentences with no filler. The primary purpose and distinguishing 'headline' concept are front-loaded, followed by a compact metric list and one key default behavior.
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?
The description covers the tool's purpose, metrics, and default behavior, which is sufficient for basic selection. But with no output schema and no annotations, it leaves out how from/to/days interact and what an agent should expect in the response beyond the KPI names.
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 75%, so the schema already documents most parameters. The description adds little beyond restating the full-history default, which the 'days' parameter already communicates. The metric list describes the output, not parameter semantics.
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 gives a clear verb+resource combination ('Headline KPIs for a site') and enumerates the exact metrics returned. The 'headline' qualifier helps distinguish it from specialized siblings like get_timeseries and get_breakdown, though it does not explicitly name them.
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 description implies this is the go-to tool for high-level site metrics, and the KPI list signals when it would be relevant. However, it gives no explicit guidance about when to prefer a sibling tool or when not to use this one.
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.
Each tool targets a distinct resource or analytical view: site management (add/list/verify) is cleanly separated from analytics (stats, timeseries, visitors, realtime, bot report, breakdown, health). Even the traffic-related getters differ clearly by granularity and intent, so an agent is unlikely to confuse them.
The naming follows a consistent verb_noun pattern: add_site, list_sites, verify_site, and all analytics tools use get_<noun>. This makes the toolset predictable and easy to navigate.
Ten tools is well-scoped for an analytics product, covering both site administration and multiple data views without redundancy or bloat. Each tool earns its place in the API surface.
The core site lifecycle is covered (add, list, verify), and the analytics side is thorough with stats, timeseries, breakdown, realtime, visitors, bot reports, and health. Minor gaps exist, such as no remove/update site or deeper filtering options, but agents can complete typical workflows without dead ends.