Skip to main content
Glama

set_curve

Replace a vocal part curve between two ticks by supplying tick-value points for dynamics, pitch bend, breathiness, brightness, and other expression parameters.

Instructions

Write a part curve: points [[tick, value], ...] relative to the part replace the curve between the first and last tick. Curves: dynamics, pitchBend, pitchBendSens, breathiness, brightness, clearness, portamento, growl, xSynth, character, air, exciter (short names DYN, PIT, PBS, BRE, BRI, CLE, POR, GWL, XSY, GEN/CHA, AIR, EXC). / パートのカーブを書きます。points は [[ティック, 値], ...](パート相対)で、最初と最後のティックの間を置き換えます。

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "track": "<track>",
      "part": "<part>",
      "curve": "<curve>",
      "points": "<points>"
    },
    "name": "set_curve"
  }
}

Input Schema

NameRequiredDescriptionDefault
partYes
pathNo
curveYes
trackYes
pointsYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.4.0

TDQS

A3.5/5.0
Behavior3/5

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

With no annotations, the description carries the full burden and does add valuable behavior: the replacement is scoped to the first-to-last tick, so points outside that span are untouched, and the twelve valid curve identifiers are enumerated. It omits what an agent most needs for a mutation call — whether the editor/project must be open or focused, whether the write is atomic or fails silently on out-of-range ticks, and what a successful response reports.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The English portion is compact and front-loads the operation and its replacement rule before the curve-name glossary, which is unavoidable given the schema has no enum. The bilingual mirror doubles the length without adding information for an English-reading agent, and the tick-range clause is buried mid-sentence rather than stated as its own point.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a five-parameter mutation tool with no annotations and no output schema, the description covers the critical semantics (points format, part-relative values, replacement range, curve vocabulary) but leaves track/part/path meanings, error conditions, and required application state unaddressed. It is adequate to attempt a call but not complete for a destructive-ish write.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 0%, so the description must compensate, and it does for the two hardest parameters: `points` is documented as [[tick, value], ...] with values expressed relative to the part, and `curve` gets a full list of accepted long and short names that the schema leaves as a bare string. It adds nothing for `track`, `part`, or `path`, which remain undocumented in both places.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource ('Write a part curve') and clarifies the write semantics: supplied points replace the curve between the first and last tick. It does not name the sibling it is not (get_curve, clear_curve), but the write verb plus the explicit overwrite-range rule makes the operation distinguishable without opening the schema.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Usage is implied by the write-and-replace wording: use this to author or overwrite automation data, and the tick-range clause hints that data outside the supplied range survives. There is no explicit alternative routing (e.g. 'to remove a curve use clear_curve', 'to read existing points use get_curve') and no prerequisites such as the project needing to be open.

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