set_parameter_real

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

With no annotations, the description carries the full behavioral burden, and it does disclose real behavior: units are display units (not raw), seconds are auto-converted, and the raw value is found by bisection 'without side effects' (implying repeated probing that does not audibly alter state). However, as a mutation tool it never states whether the target parameter persists, what happens if bisection fails or the parameter is out of range, or any performance cost of the search.

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?

Three tight sentences with no filler: the unit semantics (the crux) are front-loaded, followed by the mechanism, then the sibling routing. The parenthetical examples like '(e.g. 150, 5000)' earn their space by clarifying accepted input formats rather than 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?

There is no output schema or annotation set, so the description is the sole spec, and for a 7-parameter mutation tool it is only partially complete. Purpose, unit semantics and alternative routing are well covered, but the chain/chain_device parameters, failure behavior, and whether the discovered raw value is reported back are all left to inference.

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% across 7 parameters, so the description is the only source of meaning. It thoroughly explains the semantics of 'target' (Hz for frequencies, dB for gains/thresholds, ms for times, % for amounts) and, by extension, the kinds of 'parameter' it applies to, which is genuinely useful. It leaves 'kind', 'chain', 'chain_device', 'device_index' and 'track_index' entirely undocumented, notably the ambiguous chain vs chain_device distinction.

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 (set a parameter) and immediately distinguishes itself from siblings by declaring it works in Live's display units (Hz/dB/ms/%) rather than raw values. It also names set_device_parameters as the tool it supersedes for EQ/filter/compressor work, so an agent can tell the two apart without opening either schema.

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?

Explicitly routes the agent: 'Prefer this over set_device_parameters for EQs, filters, compressors.' This names the alternative tool and the condition that selects it, which is exactly the when-to-use-vs-alternatives guidance the dimension asks for. The only minor gap is that it does not spell out the inverse case (when raw values are preferable), but the selection rule is unambiguous.

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