ismail: agent DAW (MCP server)

Overview Schema Source Related Servers Discussions Admin

Sound Compare

sound_compare

Compare two sounds A/B to diagnose why a part doesn't match a reference: 1/3-octave bands, envelope, stereo width, and a distance score.

Instructions

A/B two sounds: 1/3-octave bands side by side (with << >> where A is >6 dB off), envelope from onset, centroid, stereo width, and one distance number. a/b are sources ('sound:', 'ref:drums', 'track:x', ...); window=[t0, t1] seconds or span=[start_bar, end_bar] (fractional) selects a slice. Reach for it when one part or one hit does not sound like the reference or the genre (a snare that sounds dated, a lead that does not sit like the record's): yours against theirs, on the window where it plays. Score the window, not the file: the envelope and every statistic over time count all of each sound, so a render or stem that runs past what the person hears (its release tail) reads apart from the clip they heard; the reply says when the lengths or tails differ and no window was given, and warns of any band more than 20 dB apart (text only). The distance is the number it has always been, so scores across rounds compare; fit_score=True scores the way instrument_fit does instead (each dB a band is past 20 dB off adds 0.15, the 25 Hz band counts for fmin=25).

Input Schema

Name	Required	Description	Default
`a`	Yes
`b`	Yes
`fmax`	No
`fmin`	No
`a_span`	No
`b_span`	No
`project`	Yes
`a_window`	No
`b_window`	No
`fit_score`	No

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 / fit_score
```
Added value: +{
+  "default": false,
+  "type": "boolean"
+}
```
First observedv0.3.0Oct 3, 2026

TDQS

A4.1/5.0

Behavior4/5

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

With no annotations, the description carries the burden well: it discloses output diagnostics, warning behavior for large band differences, the distinction between scoring a window and scoring the whole file, and how `fit_score` changes the distance calculation. It stops short of stating read-only/non-mutating behavior or any access requirements.

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 dense but front-loaded: it starts with what the tool does, then when to use it, then caveats. The single long paragraph is appropriate for a 10-parameter specialized tool, though it could be structured more cleanly.

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 10-parameter tool with no annotations, the description covers the core comparison behavior, output diagnostics, window-vs-file caveat, and scoring variants. The output schema reduces the need to explain return values, but incomplete input parameter coverage for `project` and `fmax` keeps it from being fully complete.

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

Parameters3/5

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

Schema coverage is 0%, and the description explains key parameters: `a`/`b` source syntax, `window` and `span` slice formats, and `fit_score` behavior. However, required `project` and `fmax` are not explained, and `a_window`/`b_window`/`a_span`/`b_span` are only implied by the general window/span explanation.

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 gives a specific verb and resource: A/B comparison of two sounds with 1/3-octave bands, envelope, centroid, stereo width, and a distance number. It also distinguishes the tool from related measurement approaches by naming `instrument_fit` scoring behavior via `fit_score`.

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 clearly says when to reach for it: when one part or hit does not sound like the reference or genre, and on the window where it plays. It names `instrument_fit` as the alternative scoring model when `fit_score=True`, but does not explicitly state when not to use this tool versus `compare` or other siblings.

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

Deploy Server