Skip to main content
Glama
ZahiriNatZuke

local-delegate

by ZahiriNatZuke
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Local

local_describe_image

Read-only

Describe an image, read visible text, or answer questions about it via a local vision model; the image stays server-side, so only text enters 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.

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.

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?

Annotations already declare readOnlyHint=true and openWorldHint=false, but the description adds critical behavior the annotations cannot convey: the image is read server-side and NEVER enters Claude's context, only the text answer returns, and it never generates/edits images. This context-channel disclosure is exactly the kind of trait structured fields can't express.

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-loads the most decision-relevant guidance (the PREFER clause) and then explains mechanics and scope. Efficient overall, though the preamble plus separate scope-guardrail sentence is slightly redundant and could be tightened.

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, return values need not be described, and the description fully covers the input channel, scope, and when-to-use. Nothing an agent needs to select and invoke this tool 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 description coverage is 0%, so the description must compensate, and it documents all three parameters with added meaning: accepted formats (png/jpg/jpeg/webp/gif) for path, the optional/default behavior of question, and the semantic of max_words. It does not restate the numeric default (200) or the null default, which remain 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?

States a specific verb+resource ('Describes an image or answers a question about it with a local vision model') and explicitly bounds scope with a guardrail ('ONLY image->text... NEVER generates or edits images'). Though the sibling tools (local_summarize, local_translate, etc.) are not image-oriented, the description still makes the image->text boundary unambiguous.

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?

Explicitly says when to prefer this tool ('over attaching or reading the image yourself when you only need a description, the visible text... or a specific answer') and when not to (when you need the image itself in context). The scope guardrail further clarifies the class of tasks it handles.

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