Analyze distance metric

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

Annotations indicate readOnlyHint=true, and description adds behavioral details: sampling rows, computing L2 norms, applying heuristic, and reporting availability. No contradiction; description supplements annotations well.

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?

Description is front-loaded with purpose, then details steps and heuristic, then return values. It is relatively long but every sentence adds value. No fluff.

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 the output schema exists and annotations are provided, the description covers the heuristic, sampling method, return values (metric, rationale, stats), and availability check. It is complete for the tool's complexity.

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 low (20%), but description adds meaning by explaining how schema, table, and column are used (sampling embeddings) and the role of sample_size. It clarifies sampling behavior beyond schema but could be more explicit about parameter types.

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 it recommends a pgvector distance metric (cosine, l2, inner_product) based on embedding-magnitude distribution. It distinguishes from siblings like analyze_hnsw_recall and analyze_vector_search_efficiency.

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?

Description provides context for when to use (e.g., to choose a distance metric based on embeddings) but does not explicitly exclude alternatives or state when not to use. The heuristic explains the decision process, but lacks explicit guidance versus sibling tools.

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