measure_rc_noise

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

Annotations cover safety (readOnlyHint=true, openWorldHint=false), and the description adds behavioral context beyond that: it polls for N seconds at ~50 Hz and the returned figure is a 95th-percentile deviation, not a raw reading. It doesn't mention blocking behavior during the measurement window, so it stops short of full transparency.

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?

Two sentences: the first front-loads the action, sampling rate, and return values; the second states the usage precondition. No filler.

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 and only two well-documented parameters, the description carries the return semantics (noise percentile + suggested deadband) and the usage precondition adequately. Minor gap: it doesn't say what the caller should do with the suggested deadband or how the N-second poll behaves for the caller.

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 description coverage is 100% – channels (0=roll…17=aux14, default all) and duration_s (max 60) are already documented in the schema. The description adds 'par canal' for the deadband output but no new parameter syntax or format detail, so baseline 3 applies.

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 (poll) and resource (RC channels) plus exactly what it returns: measured noise as the 95th percentile of deviation and a per-channel suggested deadband. This distinguishes it from siblings like get_rc, snapshot_rc_delta and detect_rc_mapping, which have different outputs.

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?

"À utiliser sticks au repos" gives a clear condition for correct use (the measurement is only meaningful with sticks at rest). It does not name alternatives or state when not to use it, but the placement condition is explicitly given.

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