ml_virtual_agent_nlu

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

Annotations provide readOnlyHint and openWorldHint, so description does not need to restate safety or scope. Description adds behavioral context (performance metrics). No contradictions.

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?

Single sentence, highly efficient, front-loaded with purpose. No unnecessary words.

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 simple read-only tool with two optional parameters, the description adequately conveys purpose and metrics. However, lacking output schema or return type hints, it could slightly improve by indicating the nature of the analysis (e.g., summary stats). Still, good overall.

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 coverage is 100% with parameter descriptions for days and topic_sys_id. The tool description adds no additional parameter semantics beyond what schema provides. Baseline score of 3 is appropriate.

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?

Description clearly states the tool analyzes Virtual Agent NLU performance, specifying metrics like conversation completion rates and fallback metrics. It distinguishes from sibling tools such as get_va_topic by focusing on performance analysis rather than retrieving individual topics.

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 context is implied (for analyzing NLU performance), but no explicit guidance on when to use this tool versus alternatives like get_va_conversation or list_va_conversations. Lacks when-not-to-use or alternative references.

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