link_account

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

With no annotations, the description carries the full burden. It clearly explains the flow: starts a session, returns a URL, and requires a follow-up call. It does not mention edge cases like cancellation or errors, but the core behavior is transparent enough for an agent to understand the tool's role.

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, using two clear sentences and a brief note. It is well-structured, leading with the action, then the return value, then the follow-up, and finally the alternative command. No unnecessary 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?

Without an output schema, the description effectively covers the essential context: what the tool returns (a URL), how the agent should proceed (call complete_linking), and the provider-specific alternative. This is sufficient for an agent to use the tool correctly.

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?

The input schema is empty, so there are no parameters to describe. The description adds no parameter-related meaning beyond what the schema already conveys (trivially complete). Baseline of 3 is appropriate since no additional parameter context is needed.

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 tool's purpose: to start a Plaid Link session, return a URL for user authentication, and then instruct to call complete_linking. It also explicitly differentiates from the teller provider alternative, making it distinct from sibling tools.

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?

It provides explicit when-to-use and when-not-to-use guidance: use for Plaid provider, and under PROVIDER=teller run 'plaid-mcp teller connect' instead. It also describes the follow-up step to complete_linking, giving complete usage context.

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