Create an evaluation test set (CSV for import)

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

With no annotations, the description carries the full burden. It discloses the max 100 cases, the import-once workflow, and that suggestFromWorkspace derives cases from topics, starters, and knowledge. It doesn't mention side effects like overwriting an existing file at outputPath, but the core behavioral traits are well covered.

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?

Three sentences, each earning its place: the core output format, the workflow constraint, and the suggestion behavior. Front-loaded with the most important information.

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?

For a tool with no output schema and no annotations, the description covers the essential workflow, format, limits, and the key parameter behavior. It could mention what happens on overwrite or how maxSuggested interacts with suggestFromWorkspace, but the agent has enough to call it correctly.

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 coverage is only 40%, so the description must compensate. It explains the cases structure (columns Question, Expected response; max 100) and the suggestFromWorkspace behavior, which adds meaning beyond the bare schema. It doesn't detail maxSuggested or outputPath defaults, but the schema already documents outputPath and workspace defaults.

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 a specific verb ('Write'), a specific resource (the CSV the portal's Evaluation page imports), and the exact columns and limits. It also distinguishes itself from related tools like cs_run_evaluation and cs_list_test_sets by explaining the file is imported once in the portal and runs are automated separately.

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 explicitly says test sets cannot be created through the API, so the file must be imported once in the portal, and that runs/results are automated via cs_run_evaluation. It also explains when suggestFromWorkspace is useful. This gives clear when-to-use and alternative routing.

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