Skip to main content
Glama

local_describe_image

Read-only

PREFER this tool over attaching or reading the image yourself when you only need a description, the visible text (simple OCR) or a specific answer about an image, not the image itself in your context.

Instructions

PREFER this tool over attaching or reading the image yourself when you only need a description, the visible text (simple OCR) or a specific answer about an image, not the image itself in your context.

Describes an image (or answers a question about it) with a local vision model. The image is
read server-side: it NEVER enters Claude's context, only the text answer comes back.

Scope guardrail: ONLY image->text (describe, read visible text, answer a specific question
about the image). This tool NEVER generates or edits images.

It does NOT measure: use it for content and overall layout, never to verify alignment, sizes,
distances, spacing or whether a text wraps to another line at the pixel level. The vision model
asserts misalignments and wraps that the DOM disproves; measure instead (on a web page,
`getBoundingClientRect` or `Range.getClientRects`). When the question or the answer uses the
usual words for that (Spanish or English), a warning follows the model's answer.

Args:
    path: Path to the image (png/jpg/jpeg/webp/gif), read server-side.
    question: Concrete question or focus about the image (optional; by default it describes
        it).
    max_words: Maximum length of the answer in words.

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": {
      "path": "<path>"
    },
    "name": "local_describe_image"
  }
}

Input Schema

NameRequiredDescriptionDefault
pathYes
questionNo
max_wordsNo

Output Schema

NameRequiredDescriptionDefault
resultYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. Addedv0.3.0

TDQS

A4.8/5.0
Behavior5/5

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

Goes well beyond the readOnlyHint/openWorldHint annotations by disclosing that the image is read server-side and never enters the caller's context, only the text answer returns. It also warns that the vision model asserts misalignments and wraps the DOM disproves, and that a warning is appended when measurement-style wording appears in question or answer.

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?

Opening sentence is a strong routing instruction and the structure is scannable (preference, what it does, scope guardrail, measurement caveat, Args). There is mild redundancy between the 'ONLY image->text' guardrail and earlier statements, and the warning-sentence about Spanish/English wording is slightly awkward.

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?

An output schema exists so return values need no explanation; what remains, the default behavior, context isolation, scope limits, and the measurement trap with its remedy, is all covered. Nothing an agent needs in order to call it correctly is missing.

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 0%, so the description must carry the parameters, and it does: path is qualified with accepted formats (png/jpg/jpeg/webp/gif) and server-side reading, question is marked optional with its default describe behavior, and max_words is defined as answer length in words. The max_words default (200) is only in the schema, keeping this short of a 5.

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?

States a specific verb and resource: describes an image or answers a question about it using a local vision model, and explicitly bounds scope to image->text only, never generation or editing. An agent immediately knows what the tool does and what it does not do, without opening the schema.

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?

Front-loads 'PREFER this tool over attaching or reading the image yourself' with the exact condition (you only need a description, visible text, or a specific answer). It also names a when-not case with an alternative: for alignment, sizes, spacing or wrap checks, measure instead via getBoundingClientRect or Range.getClientRects.

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