read_meters

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

Annotations already declare readOnlyHint=true and destructiveHint=false, so the bar is lower. The description adds real behavioral context beyond that: the measurement is time-boxed ('for a few seconds'), the dBFS scale convention is disclosed ('0 = clipping'), and the returned signal classifications are enumerated (clipping, hot, low, silent). It does not state whether the call blocks for the duration or how thresholds map to dBFS values, but it adds substantial context.

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?

Roughly 45 words front-loaded with the core purpose first, followed by compact scope semantics and flag types. Every clause earns its place and nothing is redundant with the schema's enum values or defaults.

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 read-only tool with 3 optional parameters and no output schema, the description is nearly complete: it establishes the metric, the scale convention, valid scopes, and what signal conditions are flagged. What is missing is the return shape (structure of the per-channel readings) and the threshold semantics for hot/low/silent, but an agent can invoke this correctly with what is provided.

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 0%, so the description must compensate, and it does for the trickiest parameter: 'channels' is expanded into 'channel strips, FX returns, buses, main LR' and 'inputs' as 'raw mic/aux/USB inputs'. 'seconds' and 'include_silent' are not individually glossed, but their names and defaults make them largely self-explanatory, and 'for a few seconds' implicitly ties to the seconds parameter.

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 verb and resource: 'Measure live levels for a few seconds' with explicit metrics (peak and average dBFS) and a scale convention (0 = clipping). It is clear and semantically distinct from the write-oriented siblings (set_fader, set_mute, set_gate) and from other read tools like gain_check, but it never explicitly names or contrasts a sibling, so it stops short of the top score.

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: if an agent needs live level readings (clipping/hot/low/silent), this is the tool. The scope explanation explains parameter choice ('channels' vs 'inputs') but provides no explicit when-to-use versus alternatives such as mixer_status, board_overview, or gain_check, and no exclusions.

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