run_sdk_business_primitive

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

The description hints at behavior: 'default is preview-only' and 'connector-backed apply requests fail closed while their manifest certification state is UNCERTIFIED' and 'future activated write still requires... approval'. However, these statements are cryptic and do not clearly explain side effects, state changes, or error conditions. No annotations are present, so the description carries the transparency burden but only partially fulfills it.

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 moderately verbose and uses dense jargon, but it is not overly long. However, the structure is disjointed, mixing factual statements ('default is preview-only') with abstract requirements ('A future activated write still requires...') without a clear logical flow. Some redundancy exists with the alias note.

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 an output schema, but the description does not explain what the return values represent, what success/failure looks like, or how to interpret the result. Given the complexity of parameters and the abstract nature of the tool, the description lacks critical context about the execution lifecycle, error handling, or expected outcomes.

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 parameter descriptions are absent (0% coverage), and the tool description does not explain any of the 9 parameters. Only 'preview_only' and 'connector_account_refs' are implicit in the prose, but their meaning and usage are not clarified. Parameters like 'primitive_id', 'project_ref', 'approval_refs' remain undefined, making correct invocation difficult.

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 states 'Run SDK implementation code for discovery, validation, and safe preview' but does not clearly specify what a 'business primitive' is or what concrete action it performs. The mention of 'canonical alias' and abstract domain terms (Spring-governed, server-owned effect classification) leave the tool's purpose ambiguous, especially given many sibling tools with similar 'run' naming patterns.

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?

No explicit guidance on when to use this tool versus alternatives. It mentions 'discovery, validation, and safe preview' but does not contrast with other run tools like 'run_sdk_project_workflow' or 'run_workflow'. The description lacks conditions or scenarios for selection, leaving the agent to guess.

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