connection_create

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

Since no annotations are provided, the description must disclose behavioral traits. It does state it is an alias of conn_create, which implies creating a connection is a mutating operationholistically. However, it does not explain any side effects, such as whether existing connections are affected, whether the connection replaces an existing one or duplicates, or whether it validates the paths. The parameter documentation is a copy of the schema and adds no extra behavioral context beyond the alias statement.

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 very brief and front-loaded: the alias statement comes first, followed by parameter descriptions. There is no fluff. However, the parameter documentation is formatted as a list of Python types with descriptions, which is functional but not perfectly structured. It earns a high conciseness score for efficiency, but loses a point for the slightly awkward formatting and redundancy with the schema.

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 is simple (two required string parameters, two optional integers), but the description is still shallow. It doesn't explain the relationship to the graph or the purpose of creating a connection, nor does it provide usage examples or edge cases. Sibling tools like node_create are also ambiguous, but for a mutating tool, an agent would benefit from knowing what success looks like (no output schema) and potential errors. The description is not complete enough for an agent to use it with confidence.

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. It lists each parameter with a brief explanation: 'Source operator path', 'Destination operator path', 'Source output index (default 0)', and 'Destination input index (default 0)'. This is minimal but useful for understanding what each parameter means, though it does not clarify the syntax of paths or the meaning of the indexes (e.g., are they zero-based output ports?). The description does add some value beyond the schema types, but not enough for complete clarity.

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 identifies the tool as an alias of conn_create, which creates a connection between an output of one operator and an input of another in a node graph. It clearly states the verb 'create' and the resource 'connection,' and the alias relationship helps distinguish it from the similarly named 'conn_create' sibling. However, it does not explicitly state what a connection is or that it operates on operator paths, though the parameter names convey this.

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 gives no guidance on when to use this tool versus other connection-related siblings such as conn_create, conn_delete, conn_get, connection_delete, or connection_get. It merely says it's an alias of conn_create, which implies they are interchangeable, but it doesn't explain why an agent might prefer this alias over conn_create (e.g., MCP compatibility). No exclusions or context are provided.

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