Dokploy MCP Server

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

Annotations provide significant behavioral information: destructiveHint=true indicates this permanently removes data, readOnlyHint=false confirms it's a mutation, idempotentHint=false suggests repeated calls may have different effects, and openWorldHint=true indicates it may affect resources beyond immediate parameters. The description adds no additional behavioral context, but since annotations cover the critical safety profile (destructive nature), the description doesn't need to repeat this. No contradiction exists between description and annotations.

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?

The description is extremely concise - just two lines showing the endpoint and parameter. However, it's under-specified rather than efficiently informative. The structure with 'Parameters:' heading is clear, but the content lacks meaningful information. It's brief but not helpful.

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?

Given this is a destructive operation (per annotations) with no output schema and minimal parameter documentation, the description is inadequate. It doesn't explain what 'unused images' means, what system this cleans (likely Docker), what the consequences are, whether there's confirmation or dry-run option, or what the response contains. For a destructive tool with open-world implications, more context is needed.

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?

The description lists 'serverId (string, optional)' as a parameter, but with 0% schema description coverage, the schema only indicates it's a string type. The description provides no semantic meaning - what serverId refers to, what happens if omitted (does it clean images on all servers? default server?), or format requirements. For a single parameter with zero schema documentation, the description adds minimal value beyond stating it's optional.

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 '[settings] settings.cleanUnusedImages (POST)' which is a tautology - it essentially repeats the tool name and adds HTTP method. It mentions 'cleanUnusedImages' which suggests removing unused images, but doesn't specify what type of images (likely Docker images) or what system this operates on. The purpose is somewhat implied but not clearly articulated.

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 guidance on when to use this tool versus alternatives. The sibling tools list shows other cleanup tools like 'dokploy_settings_cleanAll', 'dokploy_settings_cleanUnusedVolumes', and 'dokploy_settings_cleanDockerPrune', but the description provides no comparison or context for choosing this specific cleanup operation over others.

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