Dokploy MCP Server

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

Annotations indicate this is a non-readOnly, non-destructive, non-idempotent, openWorld operation. The description adds that it's a POST request, which aligns with non-readOnly. However, it doesn't explain what 'disconnect' actually means behaviorally - whether it removes configuration, stops synchronization, affects running services, or requires specific permissions. For a mutation tool with minimal annotation coverage of behavioral traits, this leaves significant gaps in understanding the actual impact.

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 brief - just two lines showing the tool path and listing the parameter. While this is concise, it's under-specified rather than efficiently informative. The structure is clear but lacks the substantive content needed for a tool description. It doesn't waste words, but also doesn't provide enough information to be truly 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?

For a mutation tool that disconnects something (potentially affecting system behavior), with no output schema, 0% parameter documentation, and minimal annotations, this description is completely inadequate. It doesn't explain what gets disconnected, why one would use it, what the consequences are, or what to expect as a result. The agent would have to guess about both the tool's purpose and its effects.

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?

Schema description coverage is 0%, meaning the single parameter 'composeId' has no documentation in the schema. The description merely lists the parameter name without explaining what a composeId is, where to find it, what format it expects, or what happens if an invalid ID is provided. The description fails to compensate for the complete lack of schema documentation, leaving the parameter essentially undocumented.

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 'compose.disconnectGitProvider (POST)' which repeats the tool name and adds HTTP method, but doesn't explain what 'disconnectGitProvider' actually does. It doesn't specify what resource is being disconnected from what, or what the effect is. The description is essentially a tautology that restates the tool name with minimal additional context.

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 zero guidance on when to use this tool versus alternatives. There are sibling tools like 'dokploy_application_disconnectGitProvider' and various 'saveGitProvider' tools, but no indication of when this compose-specific version should be used versus the application version or when reconnection might be needed. No prerequisites, conditions, or exclusions are mentioned.

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