Vector Similarity Search

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

Even though annotations already declare readOnlyHint, idempotentHint, and destructiveHint, the description adds substantial behavioral detail: automatic sanitization rules (embedding exclusion, large-list placeholders, string truncation, 8000-token limit), property selection behavior, and performance optimization (fetching top_k × 2,100 results). This goes far beyond the annotations and provides essential transparency.

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 well-structured with bold section headers, starting with the main purpose and then detailing sanitation, property selection, post-filtering, and performance. It is long but every sentence adds necessary detail for a complex tool, with no redundancy or filler.

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 tool's complexity (vector search, sanitization, property selection, pre-filtering), the description is complete. It covers all parameters, return values (node IDs, labels, properties, scores), related tool references, and a performance caveat. Since there is no output schema, the description appropriately explains what the agent should expect.

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%, providing a baseline of 3. The description adds meaningful value by clarifying default behavior for return_properties ('Returns ALL properties' vs. 'Returns ONLY specified properties'), giving a concrete example ('pageNumber,id'), and illustrating pre_filter usage with a JSON example. This helps an agent understand parameter semantics beyond the schema.

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 states the specific verb+resource: 'Performs vector similarity search on a Neo4j vector index.' It explicitly mentions embedding text via OpenAI and returning node IDs, labels, properties, and similarity scores. This clearly distinguishes it from sibling search tools like fulltext_search by focusing on vector-based similarity.

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 provides clear usage context, including default vs. specified property selection, examples for pre_filter, and references to get_neo4j_schema_and_indexes for schema checks. However, it does not explicitly state when not to use this tool or name an alternative like fulltext_search for text-based search, so it lacks explicit exclusions.

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