sd_create_graph

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

Annotations are all false, adding little context. The description discloses the core behavior (creates an empty graph) and the requirement that the package be open, but it does not describe side effects, error conditions, or what happens if a graph with the same identifier already exists. It adds minimal transparency beyond the annotations.

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 a single, concise sentence with no filler. Every word contributes to the meaning, clearly stating the action and scope.

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 output schema covers return values, and the description provides the core purpose. However, it lacks parameter-level guidance, does not discuss edge cases, and does not explicitly address usage conditions, making it adequate but not fully complete.

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%, and the description provides almost no parameter-level detail. The phrase 'explicit open package' hints at the package parameter, but it does not explain identifier or graph_type, leaving significant ambiguity for a three-parameter tool.

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 action ('Create'), the resource ('empty compositing graph'), and the context ('in an explicit open package'). It distinguishes the tool from siblings like sd_open_graph and sd_create_graph_output by specifying it creates a new graph.

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 implies usage for creating a new empty graph but does not explicitly state when to use this tool versus alternatives, nor does it mention exclusions or prerequisites beyond the package being open. There is no explicit reference to sibling tools.

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