Aggregate run-level metrics including token usage, cost, call counts, errors, and latency to evaluate performance and troubleshoot issues.
Aggregate metrics for a run: total_input_tokens, total_output_tokens, total_cache_read/write, total_cost_usd, llm_call_count, tool_call_count, error_count, total_latency_ms.
| Name | Required | Description | Default |
|---|---|---|---|
| id | Yes |
Changes observed during successful MCP inspections.
v0.3.0Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The readOnlyHint and openWorldHint annotations already convey that this is a safe read operation, so the description does not need to restate that. It adds value by listing the specific metrics returned, but it does not disclose any additional behavioral traits such as aggregation timing, error handling, or whether the metrics are computed live or stored.
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 leads with the core purpose and then lists the exact metrics. Every word earns its place, with no filler or repetition of schema details.
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?
With no output schema, the description compensates by enumerating the returned metrics, which is the most critical missing information. Combined with the single 'id' parameter and read-only annotations, an agent has nearly everything needed to invoke the tool correctly. Only a brief note identifying 'id' as the run ID would make it fully complete.
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 schema only defines 'id' as a required string with no description (0% schema coverage), so the description carries the burden of explaining it. The phrase 'for a run' correctly implies that id refers to a run ID, but it does not explicitly state this mapping or provide any format guidance. This is minimally adequate for a single simple parameter.
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 states a specific action ('Aggregate metrics for a run') and enumerates the exact output fields, making the tool's purpose obvious. It is distinguishable from siblings like invariance_run_get or invariance_run_llm_calls by its emphasis on aggregate metrics rather than raw data, though it does not explicitly name any alternative tool.
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 guidance is provided about when to use this tool versus closely related siblings such as invariance_run_get, invariance_run_inspect, or invariance_run_llm_calls. The intended use case is implied by the description but never stated as a recommendation or exclusion.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.