Run read-only Cypher queries against a repository space snapshot to explore its shared code graph, with row limits and offset pagination for scoped results.
Run the supported read-only Cypher subset against this space snapshot. max_rows must be between 1 and 25 and is a global limit for projectless calls. Use offset for scoped pagination.
| Name | Required | Description | Default |
|---|---|---|---|
| query | Yes | ||
| offset | No | ||
| project | No | ||
| max_rows | No |
Changes observed during successful MCP inspections.
v0.1.0Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With zero annotations, the description does real work: it declares read-only execution, warns that only a 'supported subset' of Cypher is accepted, and flags that max_rows is a global cap for projectless calls. It omits what happens on unsupported constructs (error vs. silent truncation), whether the snapshot is a fixed point-in-time view, and any return shape, which are the biggest risks for a query language tool.
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?
Three short sentences, all front-loaded with the highest-value fact (read-only Cypher against a space snapshot) first, then the constraint, then pagination. No filler and nothing buried.
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?
No annotations and no output schema mean the description carries the burden, and it covers safety profile, language restriction, row caps, and pagination reasonably well. It falls short on the undocumented project parameter and on sibling routing, both of which an agent needs before writing Cypher.
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 0%, so the description must compensate, and it does for three of four parameters: max_rows gets both its 1-25 range and its projectless-global-limit semantics, offset gets its pagination role, and query is scoped to a read-only Cypher subset. The 'project' parameter is never explained — notably the phrase 'projectless calls' hints at scoping behavior without stating what setting project actually changes — which is the one real gap.
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?
Specific verb and resource: 'Run the supported read-only Cypher subset against this space snapshot' tells an agent exactly what the tool does and the query language involved. It does not distinguish itself from siblings like search_graph or trace_path, so the agent gets no signal about why one would choose Cypher over those higher-level tools.
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?
There is no guidance on when to use this tool versus search_graph, trace_path, or get_graph_schema, and no note that a schema-discovery call should precede arbitrary Cypher. 'Use offset for scoped pagination' is parameter mechanics, not tool-selection guidance, so the agent must infer applicability entirely.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.