get_clip_groove_context

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

Annotations already mark this readOnly with destructiveHint=false, and the description reinforces that with 'Read' and 'does not execute them.' It adds the useful detail that the result is a 'snapshot' rather than a live state or a computed mutation. There is no contradiction, and the extra 'does not execute' nuance clarifies side-effect behavior beyond the annotations.

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 dense sentence with no filler, front-loading the read verb and the snapshot resource. The enumeration is compact, though terms like 'native callback snapshot' and 'UI-only extraction and baking' are jargon that could be unpacked.

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 specialized validation tool, it names the use case and the data domains, and the schema covers the required parameters. However, there is no output schema, and the description does not explain 'native callback' or 'UI-only extraction and baking,' which an agent would need to fully understand the returned context. The lack of any return-structure or example leaves some ambiguity.

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?

Both parameters have complete schema descriptions specifying stable IDs and their sources (list_clips, list_arrangement_clips, list_tracks). The prose lists data categories but does not add meaning or format details for the two parameters beyond what the schema already provides. With 100% schema coverage, a baseline of 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?

The description opens with 'Read' and a definite resource—a native callback snapshot—and enumerates the included data domains: clip/track names, MIDI note IDs, expression/audio state, clip timing, Groove Pool, and global musical context. This gives an agent a concrete picture of the tool's scope. It stops short of naming a sibling it is not, so differentiation from get_live_state or get_song_musical_context is left implicit.

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 explicitly names the workflow: 'Supports before/after validation of UI-only extraction and baking'. This tells an agent when to invoke the tool. It also warns that it 'does not execute' those operations, but it doesn't name alternative tools for cases where the agent needs to actually perform extraction or baking.

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