capture_midi_session

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

Adds substantial behavior beyond the annotations: the target is chosen by Live and may create or change clips across multiple MIDI tracks or add a scene, so the effect is non-deterministic and multi-target. It also discloses the readiness requirement and what is reported back (immediate slot changes, note count/digest changes), which is exactly the extra context an agent needs for a non-idempotent open-world mutation.

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?

Four sentences, front-loaded with the action and scope, then risk, reporting, and prerequisites. Dense but each sentence carries distinct information; 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?

For a complex, non-idempotent, open-world mutation with no output schema, the description covers effects, uncertainty of target, return shape, and readiness/confirmation prerequisites. An agent can plan or invoke this correctly without further 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 100%, so all four parameters (dryRun, planHash, confirmationToken, expectedStateVersion) are already documented. The description only echoes the plan/confirm distinction, adding no syntax or format detail beyond the schema; baseline 3 is appropriate.

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 (plan/invoke) plus the exact resource (Live's native Capture MIDI into Session View) and the input scope (recently played MIDI on audible tracks). No sibling tool performs Capture MIDI, so the definition is self-distinguishing without needing to name a competitor.

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 clear context for invocation ('recently played MIDI on audible tracks') and states a prerequisite ('native can_capture_midi readiness and confirmation'), plus routes note inspection to a separate tool. It does not name specific alternatives or exclusions, so it falls short of full when/when-not guidance.

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