Retrieve aggregated evaluation metrics, such as mean score and pass rate, for a specified evaluation. Use this to assess LLM quality and identify performance issues for a project.
Get aggregated evaluation metrics (mean score, pass rate, etc.).
| Name | Required | Description | Default |
|---|---|---|---|
| eval_name | Yes | Evaluation name (e.g., 'hallucination', 'qa_correctness') | |
| project_name | Yes |
Changes observed during successful MCP inspections.
v0.1.0Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the burden of behavioral disclosure. It does add some behavioral context by revealing the kinds of aggregated metrics returned ('mean score, pass rate, etc.'), but it does not mention output structure, aggregation behavior, error conditions, or any other operational details. For a simple read-only lookup this is adequate but not rich.
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, focused sentence with no filler. The core action and key examples are front-loaded, and every word contributes to understanding the tool's purpose.
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 a two-parameter tool with no output schema, the description provides a reasonable baseline: it names the action, the resource, and example metrics. However, it leaves gaps around what the return payload looks like, how the two parameters interact, and when this tool should be selected over sibling tools.
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 only 50%: eval_name has a helpful example but project_name has no description. The tool description does not compensate by clarifying either parameter's role or expected format, so the agent must rely on parameter names and general context.
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 identifies a specific verb ('Get') and resource ('evaluation summary'), and adds meaningful detail by naming the aggregated metrics ('mean score, pass rate, etc.'). However, it does not explicitly contrast itself with sibling tools like list_evaluations, so differentiation is mostly implicit.
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 intended use is implied by the phrase 'Get aggregated evaluation metrics' — an agent can infer this is for summary statistics rather than raw data. There is no explicit guidance about when to use this tool versus alternatives such as list_evaluations or get_spans, so the usage context is present but underdeveloped.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.