apply_midi_probability_pattern

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

Annotations already state readOnlyHint=false and destructiveHint=false. The description adds two meaningful behavioral traits: 'guarded' (implying a confirmation mechanism) and 'preserving pitch, timing, velocity, mute, and expression metadata' (a non-destructive guarantee). It does not explain what 'guarded' means in terms of the dryRun/confirmationToken workflow, but that is covered in the schema. The description does not contradict annotations, and it adds some context beyond the structured fields.

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, concise sentence that starts with the primary action ('Plan or apply guarded MIDI playback probabilities') and front-loads the key scope. It has no filler or redundancy. It could benefit from a second sentence on the guarded confirmation workflow, but as written it is compact and clear enough for a first pass.

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 tool's complexity (8 parameters, a two-phase dry-run/apply workflow, no output schema), the description alone is somewhat incomplete: it never mentions that applying requires a planHash and confirmationToken, or that dryRun=true returns a plan. However, the schema descriptions for dryRun, planHash, and confirmationToken explain this completely, so an agent reading the full definition (description + schema) has enough context. The description could still summarize the workflow to make the entire tool definition more self-contained, but it is not severely deficient.

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 the baseline is 3. The description does not directly explain any parameter, but it uses the word 'probabilities' which aligns with the probabilities array parameter. It doesn't add extra meaning about the relationship between noteIds and probabilities or the dryRun flow; the schema already does that. The description adds no significant semantic value beyond the schema, hence a 3.

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 and resource: 'Plan or apply guarded MIDI playback probabilities' and adds a clear scoping guarantee: 'preserving pitch, timing, velocity, mute, and expression metadata.' This distinguishes it from non-probability MIDI tools like apply_midi_velocity_curve or apply_midi_gate_pattern. However, it does not explicitly differentiate itself from the sibling plan_midi_probability_pattern, and saying 'Plan or apply' could confuse an agent about whether to call the planning tool instead.

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 gives no explicit guidance on when to use this tool versus alternatives. It does not mention that this is the apply companion to plan_midi_probability_pattern, nor does it say 'for probabilistic note occurrence use this, for deterministic gating use apply_midi_gate_pattern.' The only hint is the phrase 'MIDI playback probabilities,' which is an implied usage rather than an explicit selection rule. An agent must infer from the name and schema that this applies a precomputed probability plan.

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