Create a Link token

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

No annotations are provided, so the description carries the burden. It discloses the two-step flow (link_token then public_token exchange) and sandbox credentials, which is useful. However, it does not disclose side effects, rate limits, or what happens on the Plaid side when a token is created. The description adds some behavioral context but not rich detail; a 3 is appropriate.

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 three sentences and front-loads the core purpose and usage. The sandbox credentials sentence is useful but could be considered extra; still, it earns its place for testing. No wasted words, though the flow explanation could be slightly tighter.

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 token-creation tool with no output schema, the description covers the main flow, the alternative, and sandbox credentials. It does not explain the return value shape (link_token field) or OAuth redirect requirements beyond the schema, but the schema covers redirect_uri. The description is complete enough for an agent to call it correctly in the common case.

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 29%, so the description must compensate. It does not explain any of the 7 parameters beyond what the schema already provides. The schema already documents user_id, redirect_uri, and defaults, but the description adds no parameter-level meaning. With low coverage and no compensation, a 3 is the baseline for adequate but not helpful.

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 specific verb ('Calls /link/token/create'), the resource (Link token), and the intended use case (real Link UI vs sandbox shortcut). It also names the sibling tool it is not (sandbox shortcut), which distinguishes it from plaid_sandbox_item_create. An agent can tell this apart from siblings without opening the schema.

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 says when to use this tool ('when you want the real Link UI (web or mobile) instead of the sandbox shortcut') and gives the follow-up flow: pass the returned link_token to Plaid Link, then exchange the public_token with /item/public_token/exchange. It also provides sandbox credentials (user_good / pass_good), which is actionable context for testing. This is clear when-to-use guidance with an alternative implied.

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