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

Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, so safety is covered. The description adds behavioral context beyond annotations by explaining that results include distance from the start, and that traversal is constrained by max_depth and direction. It also mentions filtering by relationship types. It does not discuss cycles or performance, but the added context is meaningful.

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 concise and well-structured: a clear opening sentence, a succinct output summary, a usage statement, a concrete example, and a closing note on filtering. Every sentence contributes necessary information without fluff or redundancy. The example is included as a code block, improving readability.

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 8 parameters, no output schema, and graph traversal complexity, the description provides a solid overview. It explains the return value ('nodes reachable within max_depth hops, with their distance'), the example with parameters, and support for filtering. It does not detail the exact response structure (e.g., JSON fields), but the description is sufficient for an agent to understand when and how to invoke the tool. Slight gap in not mentioning default behavior (direction=both, max_depth=3) which is only in the schema.

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 baseline is 3. The description adds semantic value through a concrete example ('Start from "Alan Turing", traverse outgoing relationships up to 3 hops deep') and explains that relationship_types is a filter in UPPER_SNAKE_CASE. It clarifies how direction and max_depth work in context, enriching the bare schema descriptions.

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 tool's purpose: 'Walk the graph from a starting node, discovering connected knowledge' and specifies the output: 'Returns all nodes reachable within max_depth hops, with their distance from the start.' This distinguishes it from siblings like get_node_relationships, which likely only returns immediate neighbors, and search_graph_nodes, which is search-based.

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: 'Essential for exploring knowledge graphs — find related concepts, trace connections, discover clusters.' While it doesn't explicitly name alternative tools or state when not to use it, the context implies it is for multi-hop traversal rather than single-hop lookups. The example also clarifies typical invocation. Missing explicit exclusions, but adequate.

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