Connect workflow steps

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

Annotations already declare readOnly=false, idempotent=false, destructive=false and openWorld=true, so the mutation and novelty profile is covered. The description adds value beyond that with a prerequisite (both steps must exist) and a return statement ('the created transition including its id'), which matters since there is no output schema. It stops short of noting that non-idempotent repeated calls can create duplicate transitions or any permission requirements.

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?

Four bolded, clearly labeled sections with purpose front-loaded and zero filler; every clause carries distinct information (purpose, exclusion, prerequisite, return value, trigger conditions). Well suited to fast agent scanning.

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?

Good for routing and prerequisites, and the absent output schema is partially compensated by the Returns line. But a tool with a free-form nested 'condition' object, an undocumented 'priority' ordering parameter, and 20% schema coverage leaves the agent guessing on how to actually express a branch condition — the most important detail for this 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 only 20% — just 'id' (and only as 'Workflow UUID'). The description never explains fromStepId, toStepId, priority (no doc at all), or the shape of the nested 'condition' object, even though conditional branching is the headline use case. With four of five parameters undocumented in both places, the description does not compensate for the coverage gap.

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 a specific verb and resource ('Connect one step to another') and immediately defines the semantic content of the edge ('what happens next and under which condition'). It explicitly names the sibling it is not (plunk_add_workflow_step), so an agent can disambiguate without opening either schema.

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?

Has an explicit 'Not for' clause naming the alternative tool and a prerequisite ('Both ends must exist first'), plus a 'Use when' clause covering both the linear-wiring and conditional-branching cases. When-to-use, when-not-to-use, and the alternative are all present.

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