Skip to main content
Glama
Sign In
sketchy-mcp

sketchy-mcp

by ddkbs
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Local

Locate parts in a photo

locate

Find named regions in a photo using a local vision model. Returns a preview with boxes drawn so you can verify results, rephrase missed queries, and skip incorrect boxes.

Instructions

Find named regions in a photo with the local vision model, e.g. ['USB port', 'reset button', 'A0']. Printed text is matched exactly; describe other parts visually ('silver USB connector'). Returns a preview with the boxes drawn so you can check them: rephrase queries that missed, skip wrong boxes, and if a box marks a different part than asked, you may still use its region name with corrected label text.

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": {
      "image": "<image>",
      "queries": "<queries>"
    },
    "name": "locate"
  }
}

Input Schema

NameRequiredDescriptionDefault
imageYesImage id from find_image
queriesYesNames of the regions to find

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.8

TDQS

A4.3/5.0
Behavior4/5

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

With no annotations, the description carries the full burden and does well: it discloses the exact-match rule for printed text, that the return is a rendered preview with boxes, and how to react to misses and mislabeled boxes. It omits prerequisites such as whether a vision model must first be downloaded or loaded via the download_model/model_status siblings.

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 purpose is front-loaded with examples and the operational caveats follow in order of use. The final sentence runs long by chaining three separate recovery instructions, but no sentence is 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 two-parameter tool with no annotations and no output schema, the description covers what matters most: matching semantics and the shape of the returned preview. The remaining gap is the model-readiness prerequisite implied by the local-vision wording.

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, but the description adds real meaning: the items of 'queries' are matched as literal text for printed labels and as visual descriptions otherwise, with worked examples. The 'image' parameter's provenance is already documented in the schema.

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 concrete verb and resource ('Find named regions in a photo') and immediately bounds the mechanism ('with the local vision model'), then gives concrete query examples. This distinguishes it from siblings such as search_parts or sketch, which would otherwise sound interchangeable.

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 gives practical selection guidance on query phrasing — exact text for printed labels, visual descriptions for other parts — plus recovery steps when boxes miss or land wrong. It never names an alternative sibling (e.g., when to use search_parts instead of locate), so the when-not side is left to inference.

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