Describe an image at a URL in natural language.
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": {
"image_url": "<image_url>"
},
"name": "caption"
}
}| Name | Required | Description | Default |
|---|---|---|---|
| image_url | Yes | Public http(s) URL of the image |
Changes observed during successful MCP inspections.
Input schema / properties / image_urlAdded value: +{
+ "description": "Public http(s) URL of the image",
+ "type": "string"
+}Input schema / requiredAdded value: +[
+ "image_url"
+]Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are supplied, so the description carries the full behavioral burden, yet it discloses almost nothing: no note on whether the image must be publicly reachable, size or format limits, whether any auth is needed, or what the returned caption text looks like. 'Natural language' hints at the output shape but stops short of describing it.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
A single front-loaded sentence with no filler or repetition. It is efficient, though its brevity is closer to under-specification than tight editing.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a one-parameter, annotation-free tool with no output schema, the definition covers the basic action but leaves the return value and failure modes (unreachable URL, unsupported image type) unexplained. Adequate to attempt a call, not adequate to predict the outcome.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
There is one parameter with 100% schema description coverage ('Public http(s) URL of the image'), so the schema already fully documents it. The description's phrase 'at a URL' merely restates that without adding format, reachability, or validation details beyond the schema.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description states a specific verb ('Describe') and resource ('an image at a URL') plus the output style ('in natural language'), which resolves the ambiguity of the bare name 'caption'. It implicitly separates the tool from text-extraction siblings like ocr, but never names them.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
There is no explicit when-to-use guidance and no mention of alternatives such as ocr (text extraction) or analyze_url, both of which appear in the sibling list and could plausibly be chosen instead. The agent must infer the boundary from the single sentence.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.