CONDITION_SWITCH

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

No annotations are supplied, so the description must carry the full behavioral burden, and it does disclose substantial runtime semantics: == / != compare as strings, > < >= <= coerce non-numeric values to 0, contains/startswith/endswith are case-insensitive, and undefined variables compare as the string 'null'. It still omits how missing variables or malformed expressions surface at runtime and does not describe the variable snapshot payload beyond naming its shape.

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 opening clause states the purpose first, then operator semantics, then branch wiring, then return shape – a sensible front-loaded order. It is dense with semicolon-chained clauses and ends with a doubled full stop, but nearly every clause carries real information.

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 four-parameter branching node with no output schema, the description covers the essential grammar, branch wiring, evaluation coercions, and the return format (a variable snapshot JSON). The main remaining gap is disambiguation from CONDITION_ADVANCED_SWITCH and any statement about expression-evaluation failure modes.

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 earns above baseline by specifying expression grammar the schema only gestures at: the operator set, that the left side is a bare variable name without ${}, that the right side is an unquoted literal, and that > and < require surrounding spaces. Interpolation of ${var} in string parameters is also noted. The require and on_error parameters are not elaborated beyond their schema text.

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 and resource: routing a workflow along true/false branches by condition expression. An agent immediately understands the node type. It does not, however, distinguish itself from the sibling CONDITION_ADVANCED_SWITCH, leaving the reader to guess which branching node to pick.

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?

Operational context is clear: branches go in the node's branches map (true/false → node id), the node does not use next, and a missing branch simply ends that path. What is absent is explicit routing guidance against the alternative CONDITION_ADVANCED_SWITCH when a simple expression will not do.

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