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

Annotations already declare readOnly, idempotent, non-destructive, closed-world behavior, so the safety profile is covered. The description adds genuinely non-schema information: the 1000-vector batch cap, which an agent cannot infer from the input schema. Return format is left to the output schema.

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?

Three short sentences, each earning its place: what it does, why it matters, and the batch capability. The core operation is front-loaded before supporting context.

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 an output schema present, return values need no explanation, and annotations cover safety. The one gap is that no parameter is marked required, yet the tool needs at least one of vector or batch; the description never states that precondition.

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 100%, so the schema already explains both `vector` and `batch`, including that batch overrides vector. The description's mention of batch normalization adds no syntax or precedence detail beyond the schema, so the baseline 3 applies.

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?

States a precise verb+resource (L2-normalize a float vector) and immediately defines the output (unit vector with norm=1). This is unambiguous against siblings like vector_quantize, vector_stats, and vector_similarity, which perform clearly different operations.

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?

"Required by many vector DBs (Pinecone, Qdrant cosine)" gives concrete context for why and when an agent would reach for this tool. It stops short of explicit exclusions or naming an alternative sibling, so it is clear context rather than full routing guidance.

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