Dokploy MCP Server

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

Annotations provide clear hints: readOnlyHint=false (write operation), destructiveHint=true (permanent deletion), idempotentHint=false (non-idempotent), openWorldHint=true (may create new resources). The description doesn't contradict these but adds minimal behavioral context (e.g., it's a POST request). However, it fails to elaborate on critical aspects like what 'remove' entails (e.g., data loss, side effects) or error conditions, which would be valuable given the destructive nature. Since annotations cover core traits, the description adds some but not comprehensive behavioral insight.

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 brief but poorly structured. It includes the tool path ('[registry] registry.remove') and HTTP method, which is useful, but the parameter listing is redundant with the schema and lacks explanatory text. While concise, it's under-specified rather than efficiently informative, with wasted space on a basic parameter restatement that doesn't add value.

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 the tool's destructive nature (destructiveHint=true), one parameter with 0% schema coverage, no output schema, and complex sibling tools, the description is inadequate. It doesn't explain the outcome of removal, potential dependencies, or error handling. For a mutation tool with significant behavioral implications, more context is needed to guide safe and correct usage, especially without output schema details.

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 schema provides no descriptions for parameters. The description lists 'registryId (string, required)' but doesn't explain what a registryId is, its format, where to obtain it, or validation rules. This leaves the parameter's meaning ambiguous, failing to compensate for the lack of schema documentation. With one parameter and no schema descriptions, the description should provide more semantic context.

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 restates the tool name ('registry.remove') and provides minimal context about what it does. It mentions 'Parameters:' but doesn't explain what 'remove' actually means in this context (e.g., deleting a registry entry, unregistering a container registry). While it includes the HTTP method (POST), it lacks a clear verb+resource statement that distinguishes it from sibling tools like 'dokploy_registry_all' or 'dokploy_registry_create'.

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 description doesn't mention prerequisites (e.g., needing an existing registryId), when it's appropriate to remove a registry, or what happens after removal. It also fails to reference sibling tools like 'dokploy_registry_all' for listing registries or 'dokploy_registry_create' for creating one, leaving the agent with no context for tool selection.

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