Skip to main content
Glama
Sign In
Local Eyes

Local Eyes

by Arcanum703
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Hybrid

describe_image

Describe an image or answer questions about it from a local path or HTTP(S) URL, returning structured JSON so text-only and offline agents can interpret visual content.

Instructions

Describe an image, or answer a question about it. path_or_url: absolute local path or http(s) URL.

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_or_url": "<path_or_url>"
    },
    "name": "describe_image"
  }
}

Input Schema

NameRequiredDescriptionDefault
questionNo
path_or_urlYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

B3.2/5.0
Behavior2/5

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

No annotations are provided, so the description carries the full burden, yet it discloses nothing about behavior: no mention of supported image formats, size limits, network access for URLs, latency, cost, or whether results are deterministic. For a tool that will fetch arbitrary remote URLs and run a vision model, these omissions are significant.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Two short sentences with zero filler, and the core purpose is front-loaded before the parameter clarification. Nothing is redundant or padded.

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

Completeness2/5

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

With no annotations, no output schema, and 0% schema coverage, the description should say more: the return value is undescribed (free text? structured?), and constraints on image size, format, or URL reachability are absent. It is adequate to guess a call but not to call it reliably.

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 0%, so the description must compensate, and it does partially by defining path_or_url as 'absolute local path or http(s) URL' — real value the schema lacks. But the 'question' parameter is left entirely undefined: no indication of what kinds of questions work, whether it is free-form, or what the answer shape is.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource ('Describe an image, or answer a question about it'), which is clear enough for an agent to distinguish it from extract_text or read_ui by intent. However, it never names or contrasts those siblings, so the differentiation is inferred rather than stated.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The phrase 'or answer a question about it' implicitly tells the agent to supply the optional question parameter for targeted queries, which is useful implied usage. There is no explicit guidance on when to prefer this over extract_text, nor on prerequisites such as whether the path must exist or whether remote URLs are fetched.

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