save_midi_feel_template

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

Annotations declare a non-read-only, non-idempotent write with no destruction, but the description adds genuinely new behavioral facts: it 'Never overwrites' existing library entries (a safe-write guarantee not derivable from destructiveHint=false), rejects clips that have a native groove, and does not capture Groove Pool playback effects. These preconditions and scope limits are exactly the kind of beyond-annotation detail an agent needs.

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 the primary action before the constraint and scope clauses. Nothing is padded, though the 'stored-note' and Groove Pool wording could be slightly tightened.

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 save operation with no output schema, the description covers the core behavior, non-overwrite guarantee, rejection precondition, and capture scope, so an agent can call it correctly. The remaining gap is that no parameter-level meaning is supplied, particularly for the required grid and bars inputs that shape the saved template.

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?

The description says nothing about any of the 5 parameters - no meaning for grid, bars, name, trackId, or clipId. With schema description coverage at 60% and the required grid/bars params carrying only enum and min/max constraints, the description fails to compensate for the undocumented half, leaving parameter semantics thin.

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 (analyze and save) and resource (a MIDI clip's stored-note timing and velocity template), and names the destination (private named local library). It distinguishes itself from siblings like analyze_midi_feel (analysis only), load_midi_feel_template, and apply_midi_feel_template, which an agent can tell apart without opening other schemas.

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 via constraints ('Rejects clips assigned a native groove'), which tells the agent when the tool will fail, but it never says when to choose this over load_midi_feel_template or apply_midi_feel_template. No explicit when/when-not routing is provided, so usage is only implied.

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