transport

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

With no annotations, the description must carry the full burden of behavioral disclosure. It does add valuable context: 'Mutations run in an undo block (Ctrl/Cmd+Z reverts).' This tells the agent that changes are reversible. However, it fails to disclose other important traits: whether play/stop are read-only or state-changing, if record requires special permissions, what happens to existing selections, or any rate limits or side effects. The undo note is a positive but insufficient for full transparency.

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?

The description is a single sentence listing actions and a brief note about undo. It is front-loaded with the tool's purpose and the list of actions, then adds a crucial behavioral note. It is efficient with no wasted words. Could be slightly more structured (e.g., separate sentences) but overall concise.

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?

Given the complexity (8 parameters, nested objects, no output schema, no annotations), the description is only partially complete. It lists the actions but does not explain how to use the parameters (e.g., what position, start, end mean in the context of each action), nor does it cover return values or error conditions. The undo note is helpful but not enough to fully guide an agent in all use cases.

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 50%, meaning half of the 8 parameters lack descriptions in the schema. The description itself does not document any parameters beyond listing the action names. For parameters like bpm, end, start, position, seek_play, length_bars, the schema provides some descriptions for end, clear, start, position, but bpm, seek_play, and length_bars have no description. The description does not compensate for these gaps. Baseline 3 is appropriate given moderate coverage and no added meaning.

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+resource: 'Transport and project timing' with a clear enumeration of actions (play, stop, pause, record, set_cursor, set_time_selection, set_tempo). This is much clearer than the many sibling tools that deal with FX, automation, MIDI, etc. However, it does not explicitly differentiate from siblings like raw_command or get_status, leaving some ambiguity about when exactly to use this multi-action tool instead of others.

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?

The description implies usage by listing the available actions, but provides no explicit guidance on when to use this tool versus alternatives (e.g., raw_command). It also lacks prerequisites or conditions for each action. The presence of siblings that might overlap (e.g., get_status for transport state) makes this omission more noticeable.

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