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

With no annotations, the description must disclose behavior on its own. It does reveal that mutations are rejected against published flows and implies a mutation nature. However, it does not state what happens on success, whether the node is immediately saved, if any validation occurs per type, or the return value. This is a notable gap for a mutation tool.

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 reasonably concise and front-loaded: it states the core purpose first, then lists node types, then gives usage context and a restriction. The type list is long but necessary; no redundant filler is present.

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?

The tool is complex: it accepts 5 parameters, includes a nested position object, and has many type-specific data requirements. The description does not explain how to construct data for each node type, what position means beyond x/y, or the omitted enum values. Without an output schema, the description leaves too much unspecified for correct invocation.

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?

The description substantially explains the type enum by mapping values to human-readable meanings (delay→wait, condition→branch, etc.). However, it omits three accepted enum values (message, trigger, custom) and provides no explanation for flowId, position, data, or name beyond the raw schema. With 0% schema coverage, this 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?

The description opens with 'Add a node to a flow's graph,' which precisely names the verb and resource. The enumerated node types further clarify the tool's scope, and the purpose is clearly distinct from sibling tools like add_edge, delete_node, and update_node.

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 explicitly frames the tool for 'conversational flow building' with an illustrative example, and provides a when-not condition: 'Rejects mutations against published flows — duplicate first.' However, it does not name alternative tools for other operations (e.g., add_edge), so it lacks explicit sibling differentiation.

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