ds_create_workflow

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

With no annotations provided, the description carries the full behavioral burden and does add useful disclosures: SQL statements 'executed serially', schedule_start 'defaults to today', schedule_end 'defaults to 2030-12-31', and auto_online meaning 'auto-release workflow and schedule'. However, it does not disclose failure/conflict behavior, what occurs if both mode parameter sets are supplied, or any return-value/success indicators.

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 front-loaded with purpose and organized into mode sections and an Args list, making it scannable. But it is verbose and redundant: the Mode 1 bullet ('Multiple SQL separated by ";;;"') is nearly repeated in the Args line for sql_statements, and the Args list itself restates the mode structure.

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 complex 13-parameter, two-mode creation tool with zero annotations, no output schema, and no nested objects, the description covers most input semantics and defaults adequately. However, with no output schema the description should explain return values/success indicators, and it does not; it also omits error scenarios or duplicate-name behavior, which are notable gaps for a mutation 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 0%, so the Args list in the description is the only semantic source, and it compensates well for the key parameters: the ';;;' separator for sql_statements, the JSON array structure for tasks_json/relations_json, 'Quartz 7-field cron expression' for schedule_cron, and explicit defaults. However, several entries are tautological ('project_name: Project name', 'description: Description'), and the mutual exclusivity of the two mode parameter sets is not formally stated.

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 opens with a specific verb+resource: 'Create a workflow (supports simple SQL mode and complex DAG mode)', which clearly states what the tool does. The two modes are well delineated. However, it does not distinguish itself from the sibling ds_create_dag_workflow, which likely overlaps in DAG creation, so it doesn't fully differentiate within the tool family.

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 gives explicit in-tool guidance: 'Provide sql_statements + datasource_id' for Mode 1 and 'Provide tasks_json + relations_json' for Mode 2, and notes Mode 1 is 'backward compatible', implying legacy use. However, it never references alternative sibling tools (e.g., ds_create_dag_workflow, ds_update_workflow) and provides no when-not-to-use or exclusion guidance.

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