hydra-mcp

hydra_sketch

Destructive

Replace the current Hydra composition with a new sketch, validating code before applying. Splits sketches into editable blocks and refuses to overwrite human-written code unless take=true.

Instructions

Replace the entire composition with a new sketch: dry-run all of it, hush, then run.

Use this to start a fresh idea, not to add to one — hydra_block adds. Split the sketch into blocks with marker lines so each part can be revised on its own later:

// @block base
osc(30, 0.05, 1.2).out(o0)
// @block warp
src(o0).modulate(noise(2), 0.1).out(o1)
render(o1)

Code with no markers becomes one block called main.

If the document holds any human-written blocks this is refused (human_blocks), because a sketch would erase them. Pass take=true only if the person playing asked for a fresh start.

Input Schema

TableJSON Schema

Name	Required	Description	Default
`code`	Yes
`take`	No
`validate`	No

Output Schema

TableJSON Schema

Name	Required	Description	Default
`result`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

First observedv0.1.0Sep 14, 2026

TDQS

A4.8/5.0

Behavior5/5

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

Annotations already flag destructiveness, and the description adds valuable behavior beyond that: the tool is refused for human-written blocks to prevent erasure, it dry-runs, hushes, then runs, and it replaces the entire composition. This is exactly the kind of consequence disclosure an agent needs before invoking a destructive tool. No contradiction with annotations.

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

Conciseness5/5

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

The description is longer than average but every sentence earns its place: action, sibling distinction, block syntax with example, fallback behavior, refusal rationale, and override condition. It is front-loaded with the core action and does not pad with filler.

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 destructive, complex tool with many siblings, the description is remarkably complete: purpose, alternatives, block conventions, refusal semantics, and take override are all covered. The only notable gap is the undocumented `validate` parameter; otherwise an agent has enough context to call and interpret the tool correctly.

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 carry the load. It richly explains `code` with a concrete block-marker example and explains `take` with a clear policy. However, the `validate` parameter is never mentioned, and although 'dry-run all of it' hints at it, the agent is left guessing whether validate can be disabled and what that does.

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 opens with a strong verb and resource: 'Replace the entire composition with a new sketch'. It makes the tool's scope unmistakable ('start a fresh idea, not to add to one') and explicitly contrasts it with hydra_block. An agent can distinguish this tool from its siblings without reading schemas.

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 explicitly stated: use to start fresh, do not use to add, and use hydra_block instead for additions. The refusal condition (human-written blocks) and the exact condition for passing take=true ('only if the person playing asked for a fresh start') are also given, leaving little to inference.

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