sample

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

Beyond the annotations (readOnlyHint=false is consistent with the documented state change when `function` is supplied), the description discloses real behavioral traits: readings are paced by the host, per-reading timing varies by function and speed, sub-interval values are taken back to back, and omitted settings persist the instrument's current function/range. It does not state whether the call blocks for the whole duration (potentially 600 s) or what happens on error/timeout, which is a material gap for an agent scheduling this call.

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 a one-line summary, then behavior, then a tight Args block; the long range enumeration is verbose but justified given zero schema descriptions. A few clauses (lead naming for every function) could be trimmed for agents that never set those functions, but nothing is wasted in the core path.

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 an output schema present, the description rightly avoids explaining return values and instead covers what the schema cannot: timing, state carry-over, and per-function constraints. The remaining gap is invoking-behavior detail (blocking duration, failure modes) for a tool that can run for up to 600 seconds.

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 0%, so the description carries the full burden and does: duration_s max 600, interval_s min 0.1, function semantics including which front/rear terminals it uses, per-function legal range values, speed as PLC accuracy trade-offs, and the conditional requirement of `sensor` for temperature. This is meaning an agent could not recover from the schema alone.

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?

Opening sentence gives a specific verb + resource + output shape: 'Record timestamped readings at a fixed interval and return statistics plus all samples,' which distinguishes it from a single-shot measure. It stops short of naming a sibling such as `burst` or `measure` as the alternative, so the differentiation is implied rather than explicit.

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 context is implied through timing guidance (0.3 s vs 0.6 s per reading, back-to-back when interval is short) and the note that omitted `function` reuses the present setting, which is effectively a pointer to `measure`. However, there is no explicit 'use this instead of X when Y' routing versus `measure` or `burst`, and no stated exclusions.

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