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

The annotations only declare the generic profile (not read-only, open world, non-idempotent, non-destructive), while the description adds details that the agent could not otherwise infer: the authorization persists until revocation or account disablement, is independent of browser session length, the connection entry itself lapses after 10 minutes, historical services are not auto-claimed, and no charge can occur without confirmation. It also states a critical security boundary: passwords and verification codes are entered only on the original site. This is exactly the behavioral context that annotations cannot convey.

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 purpose is front-loaded in the opening clause, and the remaining clauses are packed with non-obvious constraints rather than filler. The middle section is a long semicolon-chained sentence, which makes it dense to parse, but nearly every clause carries real operational weight.

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 zero-parameter, open-world authorization tool with an output schema and annotations, the description covers the full flow, the validity windows, the failure modes it deliberately avoids, and how to handle the returned credentials. An agent has everything it needs in order to guide the user correctly without opening the schema.

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 tool takes no parameters at all, so there is nothing for the description to disambiguate, and a baseline of 4 applies. The mentions of connection_id and connection_credential describe the outputs to be stored privately rather than inputs, and an output schema already exists to cover the return shape.

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 first clause names a specific verb and resource: generating a first-party account connection page plus a six-digit connection code, at no cost. An agent immediately knows this is the account-linking entry point rather than a query or mutation of orders. It does not explicitly contrast itself with disconnect_account or get_connected_account, so it falls short of full sibling differentiation.

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 lays out the operating context: the user must log in to the original site themselves, enter the code, and explicitly confirm long-term authorization. It also implicitly excludes the retroactive case ('does not auto-claim historical services') and unconfirmed charges. What is missing is an explicit 'use this when…' statement or a pointer to the sibling tools that handle revocation or inspection.

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