test_scenario

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

Adds real behavioral context beyond the destructiveHint annotation: every written symbol is gated before the run starts, values are restored at the end, and stop_on_fail governs abort behavior. It also states the return shape. It stops short of naming permission/auth requirements or any rate/scope limits on the live PLC, so not a 5.

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?

Front-loaded with purpose, then dense but waste-free spec grammar; every clause describes a field, a step type, or a side effect. The brief return summary is mildly redundant given the output schema exists, but nothing is padding.

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 complex nested-argument tool with an output schema, the description covers the spec structure, gating/restore semantics, and result shape well enough to call it correctly. It leaves selection relative to sibling test_* and exp_* tools unaddressed, which is the only real gap.

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 schema exposes only an open-ended 'spec' object at 0% description coverage, so the description carries the full burden — and does: it lays out the spec grammar (name, record{symbols|prefix|pattern, mode, cycle_ms}, the full step union, final_expect, timeout_ms, restore, stop_on_fail). This is exhaustive compensation for the schema gap.

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?

Names a specific verb+resource: a scripted FB test executed against the live PLC with a parallel recording. The scope is concrete enough to distinguish it from single-shot helpers like test_expect or test_stable, but it never explicitly names those siblings, so the differentiation is inferred rather than stated.

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 description implies the scenario in which it runs (multi-step scripted sequences with writes, expectations, waits and a recording) but gives no explicit when-to-use versus test_expect / test_stable / exp_run, and no prerequisites. Usage is deducible from the described capabilities, not stated.

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