CONDITION_ADVANCED_SWITCH

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

With no annotations, the description carries the full burden and does so well: it discloses the interpolation-then-resolution rule (defined variable name → value, otherwise literal), that numeric comparisons only accept numeric-typed variables while string variables must be written `${var}`, that contains/startswith/endswith are case-insensitive and require surrounding spaces, that branching uses `branches` rather than `next`, and that results come back as a variable snapshot JSON. It could still say what happens when neither branch key matches or what the snapshot 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?

The core concept is front-loaded in the first clause and every subsequent clause carries usable semantics (typing, operators, built-ins, branching, return shape) rather than filler. It is dense and semi-colon-chained without headings, and it ends with a stray trailing punctuation, so it is packed rather than elegant.

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 7-parameter, zero-required, no-output-schema workflow node with no annotations, the description covers evaluation semantics, operator quirks, built-in predicates, branch routing, and the return form. Gaps remain around the shape of `branches` (no example object) and default routing when a branch key is missing.

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%, so the baseline is 3, but the description adds genuine meaning: it explains how `expression` relates to the `var`/`operator`/`value` trio, how each side of a comparison is resolved after interpolation, and the type pitfalls of numeric vs string variables. The `${var}` escaping rule for string variables is exactly the kind of guidance the schema cannot express.

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 states a specific resource (conditional branch node) and its mechanism: expression interpolation, comparison, and branching via `branches` keys mapped to node ids. It is clearly a conditional-branch tool, but it never mentions the sibling CONDITION_SWITCH, so an agent cannot tell from the text alone why it should pick the 'advanced' variant.

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?

Usage is only implied by the mechanics: use `expression` or the split `var`/`operator`/`value` form, and `require` when asserting a post-condition. There is no explicit statement of when this node should be chosen over CONDITION_SWITCH or over ACTION_ASSERT, and no stated prerequisites.

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