Dokploy MCP Server

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

Annotations provide basic hints (non-readOnly, non-destructive, non-idempotent, openWorld), but the description adds almost no behavioral context. It mentions 'POST' which aligns with non-readOnly, but doesn't describe what the test actually does (e.g., makes an API call to GitLab, validates credentials, returns success/failure status), what side effects might occur, or what authentication/rate limits apply. For a connection testing tool with no output schema, the description should explain what constitutes a successful test and what gets returned.

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 but under-specified rather than efficiently informative. The first line '[gitlab] gitlab.testConnection (POST)' is front-loaded but lacks substance. The parameter listing adds structure but without meaningful explanations. While there's no wasted text, the description fails to provide essential information that would help an agent use the tool correctly.

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 connection testing tool with 2 parameters (0% schema coverage), no output schema, and annotations that only cover basic hints, the description is incomplete. It doesn't explain what a connection test entails, what success/failure looks like, what the gitlabId refers to, or when groupName is needed. For a tool that likely makes external API calls and returns status information, the description should provide more context about the operation's purpose and expected outcomes.

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 both parameters, the description provides minimal parameter semantics. It lists parameter names (gitlabId, groupName) but doesn't explain what they represent (e.g., gitlabId is likely a provider ID from the system, groupName might be a GitLab group to test access to). The description doesn't clarify format expectations, examples, or how these parameters affect the connection test. For a tool with undocumented parameters, this is inadequate compensation.

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 '[gitlab] gitlab.testConnection (POST)' which is essentially a tautology - it restates the tool name and HTTP method without explaining what 'testConnection' actually does. It doesn't specify what resource is being tested (GitLab provider configuration, credentials, network connectivity) or what constitutes a successful test. The sibling tools include other testConnection tools (bitbucket, gitea, github, destination, registry, notification types), but this description doesn't distinguish this GitLab-specific version from them.

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 no guidance on when to use this tool versus alternatives. It doesn't mention prerequisites (e.g., needing an existing GitLab provider configuration), what problem it solves (verifying connectivity before deployment), or when not to use it. With multiple testConnection tools in the sibling list, there's no differentiation guidance for when to choose this GitLab-specific test over others.

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