live_tempo

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

With no annotations supplied, this description carries the full behavioral burden and does so unusually well: it discloses the side effect that the playhead is restored, the failure mode that Studio One has refused an undo immediately after a tempo edit, and the asymmetry that setting a segment back is exact. It stops short of describing what data comes back from 'at' or what error surfaces when the refused-undo case occurs, which keeps it below 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 and waste-free; the action enumeration comes first and constraints and warnings follow. The telegraphic style ('at: tempo at one or more positions') buys density at some cost in readability, and the parenthetical '(stopped)' in the opening line is never explained.

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 three-parameter mutation tool with no annotations and no output schema, this is close to complete: undo path, verification step, side effects, and sibling alternatives are all covered. Missing only the return shape of the 'at' action and the exact precondition implied by '(stopped)'.

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 largely does: it explains that positions are seconds or bars like "9.1.1.0", that 'at' accepts one or more positions, and that 'set' defaults to the playhead. The notable gap is bpm — neither the schema nor the description says it is required for 'set'/'insert' or how it interacts with segment bounds.

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 names the resource (the tempo map of the running Studio One) and enumerates every mode of the tool — 'at', 'set', 'insert' — with a specific verb for each, so an agent knows exactly what operation each enum value performs. It also names the sibling (song_read) that covers the whole saved map and time signatures, making it distinguishable at a glance.

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?

Explicit routing is present for the hard cases: removal must go through live_undo, 'and usually two steps' at that, with a stated verification procedure ('check with action at afterwards'), and whole-song or time-signature queries are redirected to song_read. It also states the default targeting behavior for 'set' (the playhead) so the agent knows a position is optional.

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