Create an edge between two nodes

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

With no annotations, the description reveals key behavioral details: structural vs runtime, self-loop rejection, and a reference to rules. It doesn't mention idempotency, response format, or existence checks, but covers core behaviors well.

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?

Four sentences, front-loaded with the core purpose. Each sentence earns its place: what it creates, use cases, when not to use, constraints/reference. No redundancy.

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?

Despite no output schema, the description covers purpose, usage boundaries, alternatives, and a validation rule. It omits return value/error scenarios but points to a rule document for more details, making it fairly complete for a moderately complex tool.

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 covers slug/source/target/type descriptions (67% coverage). The description adds significant meaning for 'type' with examples and clarifies source/target as directed nodes. However, label and metadata are left undocumented in both schema and description.

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 creates a directed edge for structural relations, with specific types (dependency, data_flow). It explicitly distinguishes from create_api for runtime calls and from node-creation tools by focusing on edges.

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?

Provides concrete use cases (module/library deps, route depending on data store, job writing a table) and explicitly says when NOT to use it ('use create_api instead for runtime request/call/integration'). Also advises restraint ('don't wire everything').

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