Skip to main content
Glama
newsbubbles

ismail: agent DAW (MCP server)

Exam Eye Crops

exam_eye_crops

Cuts matching spectrogram crops from real and generated clips into anonymized side-by-side images for blind real-vs-made checks before scoring the keyed answer.

Instructions

The blind crop check, step 1 (a gate before a real-vs-made exam): the same time window cut from the real and the made clip of each pair, as spectrogram images side by side ("1" and "2" in a random order), with the key hidden. pairs: [[real_path, made_path], ...]; windows: per pair, [[t0, t1], ...] in seconds (a word +-60 ms), else n_windows through each clip. Look at every out/q*.png and pick the side that looks real, WITHOUT opening out/key.json, then exam_eye_score(out, {1: '2', 2: '1', ...}). If you can tell from the picture, so can they. Not only before an exam: it is a measurement you can run alone whenever spectrogram's zoom triggers fire (a texture word, numbers close but the ear says no, a voice or played instrument, two rounds without progress).

Input Schema

NameRequiredDescriptionDefault
outYes
seedNo
pairsYes
windowsNo
n_windowsNo

Output Schema

NameRequiredDescriptionDefault
resultYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. Addedv0.4.0

TDQS

A4.5/5.0
Behavior4/5

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

Since no annotations are present, the description must carry the burden. It explains the behavioral concept of the 'blind' test and clarifies that this tool is part of an interactive measurement cycle, followed by calling `exam_eye_score`, providing strong workflow context.

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

Conciseness3/5

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

The description is excessively dense and mixes high-level conceptual explanations (e.g., 'The blind crop check') with low-level implementation details (e.g., 'a word +-60 ms'). While rich, the structure is not concise and lacks clear separation between purpose and instruction.

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?

Despite the structural flaws, the high complexity of the tool (blind testing, image cropping, time windows) is adequately covered by the description. An agent has sufficient context to understand the operational parameters of this measurement step.

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

Parameters5/5

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

Given the schema coverage is 0%, the description is crucial. It clarifies the structure of the input (paired clips), the nature of the 'windows' (time slices in seconds), and the intended function of the parameters, thereby adding necessary meaning beyond the empty schema fields.

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 explicitly defines the purpose: 'The blind crop check'. It describes the mechanism (side-by-side comparison of real vs. made clips), and positions it within the workflow (a 'gate before a real-vs-made exam'), making it distinct from related scoring tools.

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

Usage Guidelines5/5

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

Usage is dictated by specific triggers ('when spectrogram's zoom triggers fire') or lack of progress. It provides a clear scenario for use: when textural words or numbers are misleading, and the agent should run this tool.

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

Deploy Server

Other Tools