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

Annotations already establish that this is a non-read-only, non-idempotent mutation. The description adds useful context that the tool creates a custom MCP connection and that OAuth flows need different endpoints. It does not disclose side effects, failure behavior, or what happens when auth_method is set to oauth, but with annotations present this is a moderate level of transparency.

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 two sentences with the core purpose front-loaded. The caveat about OAuth flows is placed immediately after the main statement, and the explicit endpoint paths add practical value without excessive verbosity.

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 8 parameters, a nested headers object, an auth_method enum that includes oauth, and no output schema, the description is not complete enough. It leaves unclear how auth_method interacts with the warning about OAuth flows, what server_url and headers mean for a custom MCP server, and what response or validation behavior to expect. The tool needs more behavioral and parameter context to be safely invoked.

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 only 13%, and the description provides almost no parameter-level guidance. It does not explain name, server_url, headers, auth_method, or custom_integration_id beyond what the bare schema types and enum imply. The team_id parameter is well described in the schema, but most required and optional parameters remain semantically opaque.

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 a clear verb-resource pair: "Create a new user-provided connection (custom MCP server) for the current team." It names the resource type, the scope (team), and clarifies that this is specifically for custom MCP servers. It also explicitly contrasts with OAuth-based integrations, though it doesn't differentiate from closely named siblings like createCustomIntegration or createCredential.

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 explicitly tells agents when NOT to use this tool: OAuth-based integrations with an interactive browser flow should use the dedicated OAuth endpoints instead, and it names those endpoints. However, it doesn't provide guidance for choosing between this and other connection-related siblings such as createCredential, createCustomIntegration, or probeMcpServer.

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