delete_graph_relationshipDelete a specific relationship by its internal ID. Use get_node_relationships to find relationship IDs.
| Name | Required | Description | Default |
|---|---|---|---|
| rel_id | Yes | Internal relationship ID (from get_node_relationships) | |
| rel_type | Yes | Relationship key | |
| project_id | Yes | Project ID (UUID) | |
| environment | No | Environment: staging or production (default: staging) |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare destructiveHint=true and readOnlyHint=false, so the destructive nature is known. The description adds the identification mechanism (internal ID) and the prerequisite call, but doesn't disclose irreversibility or cascading effects beyond 'delete.' This adds context but not deep behavioral detail.
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?
Two sentences deliver the purpose and a key prerequisite with no waste. The most critical information is front-loaded, making it efficient and well-structured.
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?
The tool has 4 parameters (3 required), no output schema, and a terse description. While annotations cover safety and schema covers parameters, the description omits outcomes (e.g., success/failure behavior, permanence, async semantics). For a destructive operation, more context would be valuable, but the given essentials are present.
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 coverage is 100% with each parameter having a description, so the baseline is 3. The description reinforces rel_id's provenance by mentioning 'internal ID' and references get_node_relationships, which mirrors the schema description but doesn't add new format or constraint details.
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 uses the specific verb 'Delete' and identifies the resource as 'a specific relationship by its internal ID.' It clearly distinguishes from siblings like delete_graph_node and create_graph_relationship by naming the exact object and deletion method.
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?
It provides clear context by stating this deletes a specific relationship by ID and instructs to use get_node_relationships to find the ID. While it doesn't list explicit 'when not to use' exclusions, the directive to reference a sibling tool for ID lookup indicates a clear usage path.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.
Most tools are clearly differentiated by domain (project vs graph_project) and action (create, get, list, delete). The main ambiguity is get_project vs get_project_info, which both claim to return detailed project information. Otherwise tool boundaries are clear.
The server follows a strong verb_noun convention, with parallel naming for graph and non-graph tools (create_project/create_graph_project, deploy_staging/deploy_graph_staging). Minor deviations include bulk_create_graph_nodes and fulltext_search_graph, but patterns remain predictable.
48 tools is a heavy surface, even when accounting for the two parallel product domains (relational and graph). Many tools are near-duplicates across domains, and the count exceeds the 25-tool threshold that feels manageable. It would benefit from consolidation or sub-servers.
Both project types have full life-cycle coverage: create, schema management, deployment, rollback, and deletion, plus graph data operations including bulk, search, and traversal. Minor gaps exist, such as no update_graph_relationship and the redundant get_project/get_project_info pair, but agents can accomplish core workflows.