Skip to main content
Glama

alt_text

Generate descriptive alt text for images from URLs or local files to improve accessibility and SEO using computer vision models.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
file_pathNo
image_urlNo
max_wordsNo

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
resultYes

Implementation Reference

  • MCP tool handler for 'alt_text'. Validates input (image_url or file_path), constructs image_ref, and delegates to run_alt_text from metadata.runner.
    @mcp.tool()
    def alt_text(
        image_url: Optional[str] = None,
        file_path: Optional[str] = None,
        max_words: int = 20,
    ) -> str:
        if not image_url and not file_path:
            raise ValueError("Provide either image_url or file_path")
        if image_url and file_path:
            raise ValueError("Provide only one of image_url or file_path, not both")
        image_ref = image_url or file_path  # type: ignore
        return run_alt_text(image_ref, max_words=max_words)
  • Core implementation of alt_text generation. Supports local, Ollama, and OpenRouter backends using specific system and user prompts from prompts.py.
    def run_alt_text(image_ref: str, *, model: Optional[str] = None, max_words: int = 20) -> str:
        if _use_local_for("caption"):
            prompt = f"{prompts.ALT_SYSTEM}\n\n{prompts.alt_user_prompt(max_words)}"
            return _local_gen(image_ref, prompt)
        if _use_ollama_for("caption"):
            from cv_mcp.captioning.ollama_client import OllamaClient
            client = OllamaClient(host=str(_cfg_value("ollama_host", "http://localhost:11434")))
            res = client.analyze_single_image(
                image_ref,
                prompts.alt_user_prompt(max_words),
                model=_cfg_value("caption_model"),
                system=prompts.ALT_SYSTEM,
            )
            if not res.get("success"):
                raise RuntimeError(str(res.get("error", "Alt text generation failed (ollama)")))
            return str(res.get("content", "")).strip()
        client = OpenRouterClient()
        res = client.analyze_single_image(
            image_ref,
            prompts.alt_user_prompt(max_words),
            model=model or _cfg_value("caption_model"),
            system=prompts.ALT_SYSTEM,
        )
        if not res.get("success"):
            raise RuntimeError(str(res.get("error", "Alt text generation failed")))
        return str(res.get("content", "")).strip()
  • System prompt and user prompt template used by run_alt_text for generating factual alt text descriptions.
    from __future__ import annotations
    
    ALT_SYSTEM = (
        "You describe images for accessibility. Be concise and strictly factual. Do not infer unseen details."
    )
    
    
    def alt_user_prompt(max_words: int = 20) -> str:
        return (
            f"Describe this image in <= {max_words} words. Neutral tone. "
            "No brand/species/location guesses. Return one sentence only. If unknown, omit."
        )
Behavior1/5

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

Tool has no description.

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

Conciseness1/5

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

Tool has no description.

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

Completeness1/5

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

Tool has no description.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters1/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Tool has no description.

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

Purpose1/5

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

Tool has no description.

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

Usage Guidelines1/5

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

Tool has no description.

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

Install Server

Other Tools

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/samhains/cv-mcp'

If you have feedback or need assistance with the MCP directory API, please join our Discord server