create_dataset_run_item

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

With no annotations provided, the description carries the full burden of behavioral disclosure. It discloses the side effect of flushing the ingestion write, the legacy status of the API, and a critical limitation of alternatives. It does not mention permission requirements or failure modes, but the output schema covers return values, making this reasonably transparent.

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 two sentences with no filler. The primary action is front-loaded, and the fallback/legacy context is delivered in a single compact second sentence. Every word contributes meaning.

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?

Given the tool's complexity (6 params, 2 required) and the presence of an output schema, the description covers the essential behavioral context: legacy status, flush behavior, and trace-linking uniqueness. It could be more explicit about how this differs from create_dataset_item, but the phrase 'run item' and the parameter descriptions fill that gap adequately.

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 six parameters. The description adds some context by mentioning 'link an existing trace' (relevant to trace_id) and framing the run item as an append operation, but it does not significantly enrich the parameter descriptions beyond the schema.

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 an explicit verb and resource: 'Create a dataset run item', which clearly separates it from siblings like create_dataset_item (dataset item) and list_dataset_run_items. It also adds a distinct secondary action, 'flush the ingestion write', giving the tool a specific, well-defined purpose.

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 second sentence provides explicit when-not-to-use guidance: if the legacy API is gone, use the SDK experiment runner or OTel ingestion, and notes a key limitation (neither can link an existing trace through this API). It does not directly compare to the create_dataset_item sibling, but the phrase 'run item' and the trace-linking caveat imply when this tool is appropriate.

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