Neo4j GraphRAG MCP Server

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

The description adds valuable behavioral context beyond what annotations provide. While annotations indicate read-only, open-world, idempotent, and non-destructive operations, the description details automatic sanitization rules (large list/string handling, token limits), property selection behavior (default vs. specified properties), and the specific return format (IDs, labels, properties, scores). This goes significantly beyond the safety profile covered by 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 well-structured with clear sections (Lucene Syntax, Automatic Sanitization, Property Selection) and every sentence adds value. It's front-loaded with the core purpose, followed by essential details, and avoids redundancy. The bullet points enhance readability without unnecessary verbosity.

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?

For a search tool with comprehensive annotations and full schema coverage, the description provides complete context. It explains the search methodology, behavioral constraints (sanitization, limits), property handling, and references to related tools. While there's no output schema, the description clearly specifies what's returned (IDs, labels, properties, scores), making it fully adequate for agent understanding.

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 100% schema description coverage, the input schema already documents all parameters thoroughly. The description adds some contextual examples (e.g., return_properties='pageNumber,id') and links parameters to other tools (fulltext_index to get_neo4j_schema_and_indexes), but doesn't provide substantial additional semantic meaning beyond what's already in the schema descriptions. This meets the baseline for high schema coverage.

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 specific action ('Performs fulltext search') on a specific resource ('Neo4j fulltext index') using a specific method ('Lucene query syntax'). It distinguishes itself from siblings like vector_search by specifying the search type and from read_neo4j_cypher/search_cypher_query by focusing on fulltext indexing rather than general Cypher queries.

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 explicit guidance on when to use this tool versus alternatives. It references get_neo4j_schema_and_indexes to discover available indexes and check property warnings, and distinguishes itself from other search methods by specifying fulltext search with Lucene syntax. The context of automatic sanitization and property selection also informs appropriate usage scenarios.

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