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

The annotations already establish readOnly and idempotent behavior, and the description adds substantial detail beyond that: the response has two parts (data and reference), the catalog is grouped by kind (trigger/logic/action), and it warns that the node set changes over time so callers should not assume stability. It also surfaces subtle semantics like the difference between field templating on LOGIC nodes and raw payload paths on TRIGGER conditions.

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 long but well-structured, with the core instruction front-loaded and details organized into clear bullets. It is dense with necessary information for a complex catalog response. It loses a point because some ideas are repeated, such as 'do not rely on memory' and 'read data for the authoritative list rather than assuming,' which slightly bloat the length.

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?

With no output schema, the description carries the full burden of explaining the return value, and it does so thoroughly: it names both response parts, enumerates the contents of `reference`, explains grouping by node kind, and flags edge cases around conditions, triggers, composite fields, and examples. An agent building or editing a flow would have everything needed to call this correctly and interpret the result.

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 tool has zero parameters and the schema is empty, so the baseline is 4. The description appropriately focuses on explaining the response rather than parameters, and there is nothing misleading or missing about parameter behavior.

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 a specific verb and resource: 'Retrieve the COMPLETE catalog for authoring flows.' It clearly distinguishes itself from siblings like neuron_get_flow or neuron_list_flows by framing this as the authoritative authoring-time catalog, not a single flow or flow list.

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 states when to use the tool: 'ALWAYS call this first when building or editing a flow — do not rely on memory, the full node set changes.' This is strong, unambiguous guidance that tells the agent the tool is a prerequisite for flow-building workflows. No alternative tool could substitute.

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