ml_virtual_agent_nlu

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

Annotations already declare readOnlyHint=true and openWorldHint=true, so the description doesn't need to repeat safety. It does add context about the metrics covered (completion rates and fallback) but doesn't disclose other behavioral traits like aggregation periods or response structure. The bar is lower due to annotations, so a score of 3 is appropriate.

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?

One concise sentence, front-loaded with the main purpose. Every word earns its place, no redundant filler. Ideal for a simple read-only analytics tool.

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 should clarify what the tool returns. It mentions two metric types but remains vague about output structure. For a read-only analytics tool with 2 optional parameters, the description is adequate but has clear gaps in return value expectations.

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% (both 'days' and 'topic_sys_id' have descriptions), and the description adds no additional parameter-level detail. The baseline of 3 applies since the schema handles parameter semantics adequately.

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 'Analyse' with a clear resource 'Virtual Agent NLU performance' and mentions concrete metrics (conversation completion rates and fallback metrics). It distinguishes from siblings by focusing on performance analytics rather than raw conversation lists, though it could be more explicit about the exact output format.

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 implies use for analyzing NLU performance, but provides no explicit guidance on when to use this tool over list_va_conversations or get_va_conversation, nor any exclusions or alternatives. The context among many VA-related siblings makes this a notable gap.

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