Create Agent Eval

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

The annotations already set readOnlyHint=false and idempotentHint=false, indicating this is a non-read-only, non-idempotent operation. The description adds only the purpose ('create an eval config') and doesn't disclose additional behavioral traits such as whether existing configs are overwritten, whether a fresh config is generated each call, or any authentication requirements. This adds minimal value beyond the annotations.

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 one short sentence with no redundancy, front-loading the action and key resource. All words earn their place, so 5.

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 and a 4-parameter input that includes a nested array, the description is very sparse. It doesn't mention prerequisites (e.g., agent/session must already exist) or behavior on duplicate eval_name. However, the schema detailedly documents all parameters and their semantics, so the tool is somewhat self-contained; still, a 3 reflects the missing contextual guidance.

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 covers 100% of parameters with descriptions, so the baseline is 3. The description's mention of 'set of eval cases' aligns with agent_eval_list and 'for an agent' with agent_id, but it doesn't add meaning beyond the schema, so 3.

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 ('Create') and identifies the resource ('agent evaluation config') and its payload ('set of eval cases for an agent'). This clearly distinguishes it from sibling tools like lyzr_get_agent_eval (retrieval) and lyzr_create_agent_eval_result (creating results), earning a 5.

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 provides no guidance on when to use this tool versus alternatives, nor does it mention prerequisites or exclusions. There is no mention of setting up an evaluation before running it or alternative tools for similar purposes, so it scores 2.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.