BloodHound MCP Server

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

With no annotations provided, the description carries full burden and does well by describing the output format ('path will show all the intermediary nodes and the types of relationships'), error behavior ('If this returns a 500 or 404 error it is likely that the path does not exist'), and the tool's purpose in security analysis. It doesn't mention rate limits, authentication requirements, or performance characteristics, but provides substantial behavioral context.

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 appropriately sized with four sentences that each serve a purpose: purpose statement, use case, output description, and error handling. The parameter documentation is clearly separated with an 'Args:' section. It could be slightly more front-loaded by moving the error information to the end.

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 tool with no annotations, no output schema, and 0% schema description coverage, the description provides good coverage of purpose, parameters, and basic behavior. However, it doesn't describe the return format in detail (beyond mentioning nodes and relationships), doesn't explain what constitutes a valid Object ID, and doesn't mention pagination or result limits for potentially long paths.

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 0% schema description coverage, the description compensates well by explaining all three parameters: 'start_node' as 'Object ID of the starting node (source)', 'end_node' as 'Object ID of the ending node (target)', and 'relationship_kinds' as 'Optional comma-separated list of relationship types'. This adds crucial meaning beyond the bare schema, though it doesn't provide examples or format details for the relationship kinds.

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 ('Find the shortest path'), resource ('between two nodes in the Bloodhound graph'), and purpose ('attack path analysis'). It distinguishes itself from sibling tools like 'search_graph' or 'run_cypher_query' by focusing specifically on shortest path calculation rather than general search or query execution.

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 implied usage context ('useful for attack path analysis') but doesn't explicitly state when to use this tool versus alternatives like 'search_graph' or 'run_cypher_query'. It mentions error conditions (500 or 404) but doesn't provide guidance on tool selection criteria or prerequisites.

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