ismail: agent DAW (MCP server)

Overview Schema Source Related Servers Discussions Admin

Track Fit

track_fit

Tunes track parameters in context by rendering a stem group over specified bars and scoring it against a reference stem with CLAP and band levels, then optionally applies the best values.

Instructions

Tune a track IN CONTEXT: render the track's whole stem group (stem_map) over bars [a, b] and score it against the same window of the reference stem with the perceptual (CLAP) metric plus band levels. params: {path: [lo, hi]} with 'inst.' (inst.filter.cutoff, inst.oscs.0.detune ...), 'fx..', 'volume_db' or 'pan'. 8-16 bars and 20-40 iterations is a good budget (each iteration renders the window). apply=True writes the best values into the track. wait: when the machine is busy, stand in line this long ('10m' default, '0' refuses at once), as render does.

Input Schema

Name	Required	Default
`bars`	Yes
`seed`	No
`wait`	No	10m
`apply`	No
`iters`	No
`track`	Yes
`params`	Yes
`project`	Yes

Output Schema

Name	Required	Description	Default
`result`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

Changed1 schema field changedv0.4.0Oct 26, 2026
- addedInput schema / properties / wait
```
Added value: +{
+  "default": "10m",
+  "type": "string"
+}
```
First observedv0.3.0Oct 3, 2026

TDQS

A4.3/5.0

Behavior4/5

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

With no annotations, the description carries the full burden and does well: it discloses that each iteration renders the bar window, that apply=True writes best values into the track, and how the wait queue behaves when the machine is busy. It still leaves some mutation details implicit, such as whether overwritten values are undoable or what exactly gets replaced.

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 description is front-loaded with the core tune-and-score behavior and contains little filler. It is dense and run-on in places, but every sentence adds operational detail rather than restating the name or title.

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

Completeness4/5

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

For a complex 8-parameter tool with no annotations, it supplies the key missing context: the rendering/scoring method, nested param path syntax, iteration cost, apply semantics, and wait behavior. The output schema can cover return values, so the remaining gaps around seed and exact project/track/bar formats are relatively minor.

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 description coverage is 0%, so the description must compensate. It explains the most complex parameter well by defining the nested params format with examples for inst.*, fx.*, volume_db, and pan, and it clarifies apply, wait, bar range, and iteration budget. It omits seed and does not fully define project, track, or exact bars syntax.

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

Purpose5/5

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

The description states a specific verb and resource: tune a track in context by rendering its whole stem group over a bar window and scoring it against the reference stem using CLAP plus band levels. This distinguishes it from narrower fitting tools such as instrument_fit by explicitly scoping the operation to the track's stem group.

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

Usage Guidelines4/5

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

It gives clear usage context for in-context track tuning and recommends a practical budget of 8-16 bars and 20-40 iterations. However, it does not explicitly name when to use this instead of related tools like instrument_fit, ref_retune, or eq_match, nor does it state when not to use it.

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

Deploy Server