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

Annotations already declare write/destructive/idempotent traits, but the description adds real value beyond them: it discloses that no AI call is consumed, that a versioned snapshot labeled 'Edited by AI agent (exact)' is created, and that only existing nodes are touched. This is meaningful side-effect context not present in the annotations.

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 action is front-loaded, followed by side effects and return values in a compact three-sentence block. Slightly dense run-on phrasing, but essentially no wasted text.

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?

Despite lacking an output schema, the description explicitly enumerates the return payload (applied count, rejected list with reasons, node/edge counts, open link), covers the write side effect, and clarifies scope. An agent has everything needed to call and interpret it.

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?

With 100% schema description coverage, the schema already documents both flow_id and the item fields. The description's mention of the updatable fields and 'by node id' adds little beyond what the schema already states, 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?

States a specific verb (Change) and resource (label, type, owner, note, or status of existing nodes) with clear scope (by node id). An agent can immediately distinguish it from siblings like update_edges, add_nodes, and remove_nodes.

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?

'Change... existing nodes... by node id' implies when to use it and the 'No AI call' note hints at a contrast with AI-driven tools like ask_flow. However, it never explicitly names an alternative or states when-not to use it versus add_nodes/remove_nodes, leaving routing to inference.

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