Retrieve an evaluation definition's full detail by evaluation_id, including attack techniques, adversarial goals, prompt counts, and max turns for adversarial probe tests.
Get one evaluation definition's full detail, including its config (attack_techniques/adversarial_goals/num_prompts/max_turns for adversarial_probe evaluations).
| Name | Required | Description | Default |
|---|---|---|---|
| evaluation_id | Yes |
Changes observed during successful MCP inspections.
v0.2.2Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the full behavioral burden. It usefully discloses what the returned config contains (attack_techniques/adversarial_goals/num_prompts/max_turns for adversarial_probe evaluations), which exceeds structured data, but it says nothing about permissions, errors, or missing-definition behavior.
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?
A single tight sentence, front-loaded with the verb and resource. It is appropriately sized and free of filler, though the parenthetical detail list slightly interrupts the flow.
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?
No output schema exists, so the description should describe what is returned; it does partially by naming config fields for adversarial_probe evaluations, but leaves the rest of the definition body, error cases, and ID sourcing unaddressed.
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 0% and the single parameter is undocumented. 'evaluation_id' is largely self-explanatory by name, and the description ties the retrieved entity back to 'one evaluation definition', but no format, source, or ID-example is supplied.
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?
States a specific verb ('Get') and resource ('one evaluation definition') with the scope of detail ('full detail'). It implicitly distinguishes itself from list_evaluations by fetching a single definition, but it doesn't explicitly differentiate itself from the several other evaluation-related getter siblings.
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?
Usage is only implied: fetching a single definition's detail versus listing. There is no explicit when-to-use, no mention of prerequisites, and no routing away from siblings like get_agent_evaluation or get_evaluation_run.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.