skimguard_coverage_statsAggregate, network-wide SkimGuard scan statistics over a time window — total scans, suspicious detections, distinct locations and states covered. No identifying data.
| Name | Required | Description | Default |
|---|---|---|---|
| days | No | Lookback window in days (1-365, default 30) | |
| response_format | No | Response format: 'markdown' (default) or 'json' | markdown |
Changes observed during successful MCP inspections.
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare the tool read-only, idempotent, and non-destructive. The description adds meaningful behavioral context beyond annotations, especially the privacy guarantee 'No identifying data' and the temporal window scope, which are not captured by the annotation fields. It does not cover response format details, but that is not essential for a simple aggregate read operation.
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, well-structured sentence that front-loads the core action and outputs, followed by a short privacy-relevant clause. Every word earns its place; there is no redundancy or filler.
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 this simple read-only tool with two fully documented optional parameters, the description is complete. It communicates the aggregate scope, the time window, the specific metrics returned, and the privacy property. No output schema exists, but the list of returned measures in the description sufficiently covers return semantics.
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?
The input schema has 100% description coverage, with both parameters (days, response_format) already documented clearly. The description only reinforces the time-window concept and does not add new parameter-specific meaning beyond the schema. Baseline 3 is appropriate because the schema handles the heavy lifting.
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 ('Aggregate') and resource ('network-wide SkimGuard scan statistics') and lists concrete outputs (total scans, suspicious detections, distinct locations and states). It clearly distinguishes itself from sibling tools like skimguard_device_prevalence and skimguard_my_locations by emphasizing network-wide scope and aggregate statistics.
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 clearly implies when to use this tool: for network-wide aggregate statistics, not for individual/device/location-specific queries. It does not explicitly name alternatives or exclusions, but the 'network-wide' and 'No identifying data' phrasing provides clear contextual guidance versus the many 'my_' and location-focused sibling tools.
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.