Dokploy MCP Server

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

The annotations clearly indicate this is a destructive (destructiveHint: true), non-idempotent (idempotentHint: false) write operation (readOnlyHint: false). The description adds minimal value beyond this - it confirms it's a POST request, which aligns with the write operation indicated by annotations. However, it doesn't provide additional behavioral context such as what specifically gets pruned, whether there are confirmation prompts, what permissions are required, or what the typical response looks like. No contradiction with annotations exists.

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 - arguably too concise. While it wastes no words, it's under-specified rather than efficiently informative. The structure shows the endpoint path and HTTP method, which is somewhat useful, but lacks any explanatory content about the tool's purpose or usage. It's front-loaded with minimal information but fails to provide the essential context an agent needs.

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 destructive Docker management tool with no output schema and 0% parameter documentation, this description is severely incomplete. The annotations provide safety warnings, but the description doesn't explain what Docker resources are affected, what 'prune' means in this context, or what the consequences of invocation are. Given the complexity implied by 'DockerPrune' and the complete lack of parameter documentation, this description leaves critical gaps for an agent trying to use the tool correctly.

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?

With 0% schema description coverage for the single parameter (serverId), the description provides no information about this parameter. The description doesn't explain what serverId represents, whether it's required or optional (though schema shows optional), what format it should be in, or how to obtain valid server IDs. For a tool with undocumented parameters, the description fails to compensate for the schema's lack of documentation.

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 '[settings] settings.cleanDockerPrune (POST)' is tautological, essentially restating the tool name and title with minimal added meaning. It mentions 'POST' which indicates an HTTP method but doesn't explain what 'cleanDockerPrune' actually does - whether it prunes Docker images, containers, volumes, or all of the above. The description fails to provide a clear verb+resource combination that distinguishes this tool from its many siblings.

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?

The description provides absolutely no guidance on when to use this tool versus alternatives. With numerous sibling tools in the Dokploy system (including other 'clean' operations like cleanAll, cleanUnusedImages, cleanUnusedVolumes, cleanStoppedContainers), the agent receives no indication of what specific Docker pruning this performs or when it's appropriate to use. There's no mention of prerequisites, timing considerations, or alternative tools.

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