live_record

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

With no annotations, the description carries the full behavioral burden and does well: it discloses the mutation (a new take is written), the confirmation gate, the track-arm side effect including that the track is left unarmed, and the 600-second cap. It omits what happens on failure (transport not running, no armed track) and whether the write is undoable.

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, front-loaded with purpose then the confirmation gate then the optional behaviors. Phrasing like 'which should mean the user asked for it' is slightly loose but conveys a useful semantic about what confirm implies.

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 5-parameter mutation tool with no annotations and no output schema, the description covers the essential call-correctly information: gating, mode selection, side effects, and the stop condition. The remaining gap is error/return behavior and the undocumented `precount` flag, which is minor at this complexity.

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 already 80%, and the description adds real meaning on top: `from` accepts seconds or bar positions, `seconds` is optional and its absence means indefinite recording, and `track` is armed then left unarmed. Only `precount` is left unexplained in both schema and description.

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: recording a new take into the running Studio One song. It is clearly distinguishable from read-only siblings like live_takes or live_transport, though it doesn't name the nearest alternative, live_record_setup, so the agent must infer the split.

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?

Gives a hard precondition (confirm: true, which should mean the user asked for it) and describes the two operating modes: stop after `seconds`, or record until live_transport stop. It stops short of saying when to use this versus live_record_setup, which is the main nearby ambiguity.

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