processSequence

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

With zero annotations, the description carries the full behavioral burden and only partially meets it. It usefully discloses two traits: nesting is permitted exactly one level, and edit actions are wrapped and rolled back per action — but it does not say whether a failing action aborts the whole sequence, whether successful earlier actions persist, whether the call is idempotent, or what authorization/session state is required.

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 short sentences with the envelope shape and the two key behavioral rules front-loaded, no filler. It loses a point because the second sentence outsources essential information to an external document rather than earning its place with self-contained content.

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?

This is a high-complexity tool — 35 action variants, one required parameter, no annotations — and the description is far too thin for it. An output schema exists so return shapes needn't be explained, but the reliance on an out-of-band markdown file leaves an agent unable to determine action semantics, error/rollback boundaries, or cursor-state effects from the definition alone.

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 0%: 35 action variants are enumerated structurally with const discriminators and required fields, but none of the fields are described anywhere. The description only restates the {action, params} envelope and delegates all meaning (pitch, advanceCursorAfterAction, ratio, harmonyType) to docs/ACTIONS.md, so it adds almost nothing beyond the schema's structure.

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 and resource: processing a sequence of plugin actions, with each entry shaped as {action, params}. This clearly distinguishes it from the single-purpose siblings (ping_musescore, get_score, run_qml) by signaling batched execution, though 'process' is generic enough that the domain (score editing) must be inferred from the action names.

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?

No guidance on when to choose a sequence over calling individual tools, no preconditions (must a score be connected first?), and no exclusions. The only routing information is a pointer to docs/ACTIONS.md, which is an external artifact the agent may not have access to, so it cannot be relied upon as actionable guidance.

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