Summarize agent activity over a time window with run counts, errors, cost, and latency to answer what's happening across your agents.
Cross-run rollup over a time window: total runs, nodes, errors, cost, latency, etc. Use this to ground "what is happening across my agents" questions.
| Name | Required | Description | Default |
|---|---|---|---|
| window_hours | No | Lookback window in hours (default 24, max 90 days). |
Changes observed during successful MCP inspections.
v0.3.0Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint and openWorldHint, covering the safety profile. The description adds that the tool aggregates across runs over a time window, which is useful, but it does not disclose edge behaviors such as result ordering, truncation, or the meaning of 'etc.' in the returned data.
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 sentences with no filler. The core purpose is front-loaded, followed immediately by a concrete usage cue. Every sentence earns its place.
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 this is a simple read-only tool with one optional parameter fully documented in the schema and useful annotations, the description is nearly complete. It does not define a return format or enumerate all metrics, but the provided examples plus the 'etc.' are adequate for an agent to select and invoke the tool.
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 only parameter, window_hours, is fully described in the schema with default and range details. The description's mention of 'time window' aligns with the parameter but adds no new semantic information beyond the schema, so the baseline 3 applies.
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 clearly communicates an aggregate metrics view: 'Cross-run rollup over a time window' plus the metric types (runs, nodes, errors, cost, latency). It implies a distinction from per-run or agent-specific metrics, though it does not explicitly name sibling tools like invariance_run_metrics or invariance_metrics_agents.
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 gives an explicit, practical use case: 'ground "what is happening across my agents" questions.' This tells the agent when to choose the tool, but it does not state when not to use it or name alternatives, so it falls short of full routing guidance.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.