Fulltext Search

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

Beyond the readOnlyHint and idempotentHint annotations, the description discloses substantial behavior: automatic sanitization of large lists/strings, a hard 8000-token response limit, and the difference in property return when return_properties is specified vs. not. It also clarifies that results may be dropped to enforce limits, which is critical for an agent to understand.

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 clear sections (Lucene syntax, sanitization, property selection, return format). Every section contributes essential information without fluff. Despite being longer than typical descriptions, it is appropriately sized for a tool with this many behavioral nuances, and the main purpose is front-loaded.

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 absence of an output schema, the description sufficiently explains return values (IDs, labels/types, properties, relevance scores). It also covers sanitization limits, property selection, and points to a sibling tool for index metadata. The description leaves few gaps for an agent to invoke the tool correctly.

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?

The schema already covers all four parameters (100% coverage), so baseline is 3. The description adds meaningful semantics, especially for return_properties: it explains default behavior (returns all sanitized properties) and the effect of specifying a comma-separated list. The example 'pageNumber,id' further clarifies usage, exceeding baseline.

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 opens with a specific verb+resource: 'Performs fulltext search on a Neo4j fulltext index using Lucene query syntax.' This precisely distinguishes it from sibling tools like vector_search (semantic search) and get_neo4j_schema_and_indexes (schema inspection), while also detailing supported query features.

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 clearly implies when to use this tool (fulltext search on a Neo4j index) and even directs users to get_neo4j_schema_and_indexes for property warnings and index names. However, it does not explicitly state when *not* to use it or contrast with alternatives like vector_search, leaving some ambiguity for an agent comparing search tools.

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