Create Second-Generation Package

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

Annotations already signal a non-read-only, non-idempotent write operation. The description adds useful context about what a package is ('bundles metadata for distribution') and the difference between managed/unlocked, but it does not disclose potential side effects, authentication needs, or what happens to existing packages. It does not contradict 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 clearly structured with a purpose-first opening and a parameter list. It is reasonably concise, but the parameter list is redundant given the schema, which slightly reduces efficiency. Overall, every sentence contributes to understanding the tool's purpose and usage.

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 description covers the core purpose and the critical decision between managed and unlocked packages. However, since there is no output schema, the description does not explain what the tool returns or how to verify success. It also omits prerequisites like needing an authenticated org. These are notable gaps for a creation 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 description coverage is 100%, so the schema already documents all parameters. The description repeats the parameters without adding significant new meaning beyond what is in the schema (e.g., 'path: source path for the package, e.g. force-app' is identical to the schema description). No extra syntax or nuanced details are provided.

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 specific action (creates), the resource (second-generation package), and the method (SF CLI). It also differentiates from siblings by specifying 'managed or unlocked' and explaining the distinction between package types, which helps disambiguate from tools like sf_create_package_version.

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 provides practical guidance on when to use each package type ('Managed packages support namespacing and AppExchange listing; unlocked packages support source-tracking without namespacing'), which helps the agent choose the correct packageType. However, it does not explicitly mention when not to use this tool or contrast it with alternatives like sf_create_package_version.

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