create_workflow

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

Annotations already declare destructiveHint=true, non-idempotent and open-world, and the description adds beyond them: edition/license gating and 404/empty-list failure modes. It does not reconcile the destructive flag with a pure 'add' operation (e.g. what gets overwritten, whether duplicate names collide) or explain the non-idempotent behavior on retry.

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?

Five short sentences, front-loaded with the action and endpoint, with no filler. Slightly telegraphic ('Add workflow.'), but every sentence carries 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 mutation tool with a deeply nested, undescribed body (WorkflowNode, WorkflowEdge, TaskPrams), no output schema, and destructive annotations, the description should at least sketch the node/edge model and required body fields. Instead it leaves the agent to infer the entire payload shape from a parameterless schema.

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 0% and the body is a nested WorkflowTemplate with nodes/edges, so the description carries the load; 'supply API fields in body; JSON-encoded string fields must remain strings' is genuinely useful wiring guidance. But it says nothing about project_id, the nodes/edges structure, or which template fields are required, so it only partially compensates.

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?

States the resource (workflow) and the endpoint POST /project/{project_id}/workflows, but the verb 'Add' is close to restating the tool name and it never says what a workflow is (a node/edge graph) or how it differs from neighboring create_* tools like create_template or create_task.

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?

It gives real preconditions — availability varies by Semaphore edition, license and permissions, and Community routes may 404 or return empty lists — which is useful when-to-use context. However, it never says when to choose create_workflow over create_template/create_task or what to do when the route 404s.

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