Skip to main content
Glama

analyze_image

Get text answers about images via a vision model chain with paid fallback and retries. Use local paths or URLs and your own prompt for OCR, UI review, or screenshot questions.

Instructions

Get a text answer about an image using a vision model chain (free OpenRouter models first, then a cheap paid fallback, with retries). Use it when you cannot see the image yourself: UI/design review, OCR, "what is on this screenshot", comparing a render to an expectation. Pass a local file path or an http(s) URL. YOU write the prompt for your task. Returns { content, servedModel, attempts, tried }.

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": {
      "prompt": "<prompt>",
      "image": "<image>"
    },
    "name": "analyze_image"
  }
}

Input Schema

NameRequiredDescriptionDefault
imageYesLocal file path (absolute or relative) or http(s) URL of the image
promptYesInstruction/question for the vision model (you write this)

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv1.0.0

TDQS

A4.6/5.0
Behavior4/5

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

No annotations are supplied, so the description carries the full burden, and it does most of it: it discloses the model-selection strategy, that free models are tried before paid ones, that retries occur, and it names the exact return fields including attempts/tried. It stops short of failure modes, per-call cost implications, rate limits, size/format limits, or whether the image leaves the local environment — meaningful gaps for an image-upload tool.

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?

Three tight sentences plus a return-shape clause, front-loaded with the capability, then usage, then input, then output. No filler, no restatement of the tool name, and the return signature is included at near-zero word cost.

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?

There is no output schema, and the description compensates by sketching the return object ({content, servedModel, attempts, tried}). Combined with both required parameters being documented in the schema, an agent has enough to invoke it correctly. Error behavior and image constraints remain undescribed.

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 baseline is 3; the description still adds real meaning by clarifying that 'image' accepts a local path or http(s) URL and, more importantly, that the agent is responsible for authoring a task-specific prompt. That last point is semantic guidance the schema does not convey.

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 — 'Get a text answer about an image' — and immediately names the mechanism (vision model chain with free-first, paid fallback, retries). An agent knows exactly what capability this provides, and even the unusual architectural detail is not left implicit.

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?

Gives an explicit routing condition ('Use it when you cannot see the image yourself') followed by four concrete task examples (UI/design review, OCR, screenshot description, render comparison). With no sibling tools in the catalog, there are no alternatives to name, so nothing further is required.

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