Dokploy MCP Server

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

Annotations indicate this is not read-only, not destructive, not idempotent, and open-world. The description adds that it's a POST operation, which implies mutation, aligning with readOnlyHint=false. However, it doesn't clarify what 'stop' means behaviorally (e.g., graceful shutdown, service interruption, or data persistence). With annotations covering safety aspects, the description provides minimal additional context.

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 and structured with a clear parameter list, avoiding unnecessary verbosity. However, it could be more front-loaded with the tool's purpose rather than starting with bracketed context. It efficiently conveys the HTTP method and parameter but misses an introductory explanation.

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 potential impact (stopping a database) and lack of output schema, the description is insufficient. It doesn't explain the outcome (e.g., success/failure indicators, error conditions) or side effects. With annotations providing some safety context but no behavioral details, the description leaves critical gaps for an agent to use the tool effectively.

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%, but the description lists the parameter 'postgresId' as required. It doesn't explain what this ID represents (e.g., instance identifier, database name) or where to obtain it. With only one parameter and no schema descriptions, the description adds basic acknowledgment but lacks meaningful semantic details.

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 and title ('postgres.stop') without adding meaningful context about what 'stop' entails. It mentions the HTTP method (POST) but doesn't clarify whether this stops a running PostgreSQL instance, pauses it, or terminates it. The purpose is tautological rather than explanatory.

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?

No guidance is provided on when to use this tool versus alternatives like 'dokploy_postgres_start' or 'dokploy_postgres_changeStatus'. The description lacks any context about prerequisites, dependencies, or scenarios where stopping PostgreSQL is appropriate versus other actions.

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