Query related knowledge graph nodes up to a given depth to identify textures rendered by functions or crashes linked to memory addresses.
Query related nodes in the Knowledge Graph up to a given depth (e.g. what textures does this function render? What crashes are linked to this address?).
| Name | Required | Description | Default |
|---|---|---|---|
| depth | No | Traversal depth (1 to 4, default 1) | |
| nodeId | Yes | Target node ID |
Changes observed during successful MCP inspections.
v1.0.0Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are supplied, so the description carries the full behavioral burden. 'Query' implies a read, but nothing states read-only semantics, whether traversal follows edge direction, what edge/node types are returned, or whether large depths are rate-limited or expensive. For a graph traversal with zero annotation coverage this is a meaningful gap.
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?
A single sentence with the core purpose front-loaded, followed by two short illustrative examples in parentheses. Every clause earns its place and nothing is padded.
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 simple two-parameter read tool with a fully described schema, the definition is close to sufficient, but with no annotations and no output schema the agent still cannot predict the shape of the response (neighbor node list? edges with types?) or the cost of higher depth values.
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 both parameters are already documented, including the depth range (1 to 4, default 1). The description reinforces 'depth' as a traversal bound rather than raw numeric input, which adds modest meaning, but adds nothing about nodeId format or what a depth of 2 versus 4 actually expands to.
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 names a specific verb and resource ('Query related nodes in the Knowledge Graph') plus a traversal bound ('up to a given depth'), and the two parenthetical examples concretize what 'related' means. It is clearly distinct from the graph mutation siblings (graph_node_upsert, graph_edge_upsert, graph_ingest), though it never names them explicitly.
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 examples ('what textures does this function render?', 'What crashes are linked to this address?') implicitly convey when to reach for this tool, which is genuine usage signal. However there is no explicit when-not guidance, no prerequisites (does the node need to exist first via graph_node_upsert?), and no mention of alternatives.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.