Skip to main content
Glama

fix_style

Repairs code in one of your finished styles by reading the note, fixing the code, running tests, checking a test shot and redrawing pictures, with changes applied only after the fix passes.

Instructions

Ask Claude to fix a problem in one of the person's own finished styles, like Dinoctor's Fix a problem: it reads the note, fixes the code, runs the tests, checks a test shot and redraws the pictures (about 10 minutes of the person's Claude usage). The style stays as it was until the fix passes. The first call only says what will happen; call again with confirm: true after the person agrees. Follow it with style_status. For a stopped build use continue_style; for a new style use make_style.

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": {
      "id": "<id>",
      "words": "<words>"
    },
    "name": "fix_style"
  }
}

Input Schema

NameRequiredDescriptionDefault
idYesThe person's own style id from my_styles (built-in styles can't be used here).
wordsYesWhat's wrong, in plain words.
confirmNotrue only after the person agreed to use their Claude usage.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changedv0.1.2
    • addedInput schema / properties / confirm / description
      Added value: +"true only after the person agreed to use their Claude usage."
    • addedInput schema / properties / id / description
      Added value: +"The person's own style id from my_styles (built-in styles can't be used here)."
  2. First observedv0.1.0

TDQS

A4.4/5.0
Behavior3/5

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

Annotations already declare readOnly=false, destructive=false, idempotent=false, so the agent knows this is a non-destructive mutation that is not safe to retry blindly. The description adds real context beyond that: a dry-run first call, per-call confirmation gated on consent, roughly 10 minutes of the person's Claude usage, and the guarantee that the style stays as it was until the fix passes. It does not say what happens on failure mid-run or how partial results are left behind, which keeps this at a solid 3.

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?

Front-loaded with the action and the work it performs, then the confirmation protocol, then sibling routing, which is a logical order. Slightly wordy in the parenthetical asides about the 10 minutes of usage and the "like Dinoctor's Fix a problem" reference, but nothing is redundant enough to cut.

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

Completeness5/5

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

For a 3-parameter, non-destructive async-ish operation with no output schema, the description covers consent gating, time and usage cost, atomicity of the style until success, and the required follow-up call. An agent has everything needed to invoke it correctly without guessing.

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 100%, so the baseline is 3. The description earns one more by explaining the two-phase meaning of confirm (first call only says what will happen; resend with confirm: true only after the person agrees) and by scoping id to the person's own style from my_styles, which the schema states but the description reinforces as a hard constraint.

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?

Names a specific verb and resource ("fix a problem in one of the person's own finished styles") and enumerates the concrete work performed: reads the note, fixes the code, runs tests, checks a test shot, redraws pictures. It explicitly distinguishes itself from nearby siblings by naming continue_style (stopped build) and make_style (new style).

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?

Gives explicit when-to-use and when-not-to-use routing: stopped build goes to continue_style, new style goes to make_style, and it prescribes a follow-up call to style_status. It also spells out the two-call protocol (first call previews, second call with confirm: true executes after the person agrees).

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