remove_node

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

With no annotations, the description carries the burden and does meaningful work: it discloses that references are not fixed and that validation will surface dangling refs afterwards. It leaves unstated whether connected edges are cascaded away, whether removal is irreversible, and what the response contains.

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?

Two short sentences, zero filler, and the key limitation is front-loaded right after the action so it can't be missed. Every clause earns its place.

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 two-parameter mutation with no output schema or annotations, the description covers the critical gotcha (dangling references needing validation). Minor gaps are the lack of return/pagination info and the unstated fate of connected edges.

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 100%, and both params (workflow_id, node_id) are already documented in the schema, including the 'from create_workflow' hint. The description adds no additional parameter meaning, so baseline 3 applies.

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 names a specific verb and resource ('Remove a node from a dynamic workflow') and clearly distinguishes it from sibling mutations like add_node or connect_nodes without needing to name them explicitly. It stops short of an explicit 'don't use for X' contrast, but the operation is unambiguous.

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 caveat that validation will report dangling refs implies the follow-up validate_workflow call, and the workflow context tells an agent where this fits. However, it never states prerequisites (e.g., workflow must exist/be editable) or when to remove versus rewire a node.

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