Analyze rerank NDCG

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

Annotations declare readOnlyHint=true and openWorldHint=false, and the description adds behavioral details: it reads from mcpg_rag.rerank_events, returns zero counts when no labeled rows exist, and surfaces specific indicators. No contradictions with 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 two sentences, clear and front-loaded, but slightly verbose. Could be trimmed without losing meaning. Still efficient.

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?

Given an output schema exists, the description does not need to explain return values. It covers key behavioral aspects and constraints (reads specific table, handles missing data). Lacks mention of performance or window implications, but is complete for its purpose.

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?

With only 20% schema description coverage, the description does not explain the parameters k, days, model, database, or retrieval_index beyond what the schema provides. The schema has descriptions only for database. The description adds no parameter semantics, which is insufficient for an agent to correctly invoke the tool.

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 states the tool computes NDCG@k comparing bi-encoder vs cross-encoder ordering, reports a delta, and surfaces specific indicators. It distinguishes itself from sibling tools like analyze_reranker_lift by focusing on NDCG and the delta.

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 explains what the delta means (positive vs negative) and indicates critical vs good evidence. However, it does not explicitly state when to use this tool over similar alternatives, such as analyze_reranker_lift, nor does it provide when-not or prerequisites.

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