Dokploy MCP Server

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

Annotations provide readOnlyHint=false, destructiveHint=true, idempotentHint=false, and openWorldHint=true, indicating this is a destructive, non-idempotent write operation that may have side effects. The description adds value by specifying the HTTP method (POST), which aligns with the annotations (non-read-only, destructive). It doesn't contradict annotations but also doesn't provide additional behavioral context like rate limits, authentication needs, or what exactly gets 'killed' (e.g., build process, resources). With annotations covering core traits, the description's addition of POST method is helpful but not extensive.

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 concise with two lines: one for the tool signature and one for parameters. However, it's under-specified rather than efficiently informative—the first line '[compose] compose.killBuild (POST)' is somewhat redundant with the tool name, and the parameter listing adds little value. While not verbose, it lacks essential details that would make it truly helpful, making it more sparse than optimally concise.

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 complexity (destructive operation with one parameter), annotations provide good coverage for behavioral traits, but there is no output schema. The description is incomplete: it doesn't explain the outcome of 'killBuild', error conditions, or return values. With 0% schema description coverage and no output schema, the description should do more to clarify parameter semantics and tool behavior, but it falls short, leaving significant gaps for the agent.

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 'composeId (string, required)' but adds no semantic meaning—it doesn't explain what a composeId is, its format, or where to find it. For a single parameter with no schema documentation, the description fails to compensate, leaving the parameter's purpose unclear.

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.killBuild (POST)' which partially indicates the action (killBuild) and resource (compose), but it's vague about what 'killBuild' specifically does—whether it terminates a build process, cancels a deployment, or something else. It doesn't distinguish from sibling tools like 'dokploy_application_killBuild' or 'dokploy_compose_cancelDeployment', leaving ambiguity. The description is minimal and lacks a clear, specific verb+resource combination that defines the tool's exact purpose.

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 does not mention any context, prerequisites, or exclusions. Given sibling tools like 'dokploy_application_killBuild' and 'dokploy_compose_cancelDeployment', the absence of usage guidelines is a significant gap, leaving the agent to guess based on tool names alone.

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