ecp_mongo_create_user

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

With no annotations provided, the description carries the full behavioral burden. It discloses three important behaviors: the automatic prefix applied to db_username, the grant of readWrite on the account's default database, and the absence of a read-only role option in MongoDB (contrasting with MySQL/Postgres). These are non-obvious and help an agent predict outcomes. It does not mention failure modes (e.g., if the user already exists) or exact success response, but for a create operation it covers the key side effects.

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—two sentences with no filler. It front-loads the main purpose and then adds critical behavioral details. The second sentence is a bit long but still efficient, using a dash to clarify the contextual difference from other DBs. It does not repeat what the name already implies and earns every word.

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 simple two-parameter create tool with no output schema and no annotations, the description covers the essential operational facts: the action, the auto-prefix, the privilege scope, and the platform-specific limitation. It does not mention required permissions or error handling, but given the simplicity and the sibling tools that handle other database assignments (e.g., ecp_mongo_assign_user_to_database), an agent has enough to call it correctly. Minor gaps exist (e.g., password format), but overall it is complete.

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 coverage is 0%, so the description must compensate. It provides meaningful context for db_username by explaining the auto-prefix behavior, which is essential for correct input. However, it gives no information about the password parameter (e.g., constraints, length, or that it is required), nor does it explain any interaction between the two parameters. Since only one of two params is explained, and the other is left to the schema (which is empty), the description only partially compensates.

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 clearly states the verb and resource: 'Create a MongoDB user.' It distinguishes this tool from close siblings like ecp_mongo_assign_user_to_database and ecp_mongo_update_user_password by specifying the immediate creation action and its readWrite grant. It also differentiates from MySQL/Postgres user creation by noting the lack of a read-only role option, so an agent can tell exactly what this tool does.

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 implies usage context—it grants readWrite on the default database and highlights the lack of a read-only role option, suggesting this is for creating a standard user with write access. However, it does not explicitly state when to use this tool versus alternatives like ecp_mongo_assign_user_to_database or when not to use it (e.g., for read-only access). No direct references to sibling tools or exclusions are given, so an agent must infer the boundary.

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