Skip to main content
Glama
Sign In
Slicewise

Slicewise

by gjlmotea
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Local

Diagnose a print failure from its symptom

bambu_diagnose
Read-onlyIdempotent

Diagnose 3D-printing symptoms by returning ordered, cost-aware remedies with mechanisms and suggested values; identifies issues no parameter can fix and avoids guessing.

Instructions

Takes an observed symptom (warping, stringing, layer separation, elephant's foot, holes in the top surface, ...) and returns an ordered list of remedies, each with its mechanism, a suggested value and its cost. Use it when the user describes what went wrong rather than which parameter to change; apply one remedy at a time. If no known symptom matches, it says so instead of guessing. It also points out problems that no parameter can fix. No side effects.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "bambu_diagnose"
  }
}

Input Schema

NameRequiredDescriptionDefault
symptomNoThe symptom in natural language, e.g. "the bottom layer bulges outward" (elephant's foot). Chinese descriptions are matched too.
materialNoThe material, e.g. PLA / ABS / PETG / TPU; a material-specific note is returned when one exists.
symptomIdNoA known symptom id; skips text matching.

Output Schema

NameRequiredDescriptionDefault
noteNo
matchedYes
availableYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A4.4/5.0
Behavior4/5

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

The annotations already declare read-only, idempotent, non-destructive, closed-world behavior, so the closing 'No side effects' is largely redundant. Beyond that, the description adds real behavioral detail the annotations do not: results are ordered, each remedy carries a mechanism and cost, and unknown symptoms produce an explicit no-match rather than a guess.

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?

Three compact sentences that are front-loaded with the input/output contract, then the selection rule, then the edge cases. The only wasted words are the trailing 'No side effects,' which restates the annotations.

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?

With an output schema present, the description need not specify return shapes, yet it still characterizes the remedy entries usefully. Combined with the no-match and unfixable-problem cases, an agent has everything needed to decide when to call it and how to interpret results.

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 description coverage is 100%, including the natural-language symptom examples and the material-specific note, so the schema already carries parameter meaning and the baseline is 3. The description's symptom list widens awareness of accepted inputs slightly but does not explain symptomId, material values, or how text matching is skipped.

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 input (an observed print symptom such as warping, stringing, layer separation) and a specific output (an ordered list of remedies with mechanism, suggested value, and cost). It explicitly contrasts itself with the parameter-centric siblings by saying to use it 'when the user describes what went wrong rather than which parameter to change.'

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?

It gives both a when-to-use rule (symptom-described failures, not parameter requests) and an operational constraint: 'apply one remedy at a time.' It also documents fallback behavior when nothing matches and notes that it flags problems no parameter can fix, so the agent knows what it will and will not get.

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