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

Annotations already declare readOnlyHint=true and destructiveHint=false, so the description does not need to restate safety. It adds genuine context beyond the annotations: no authentication is needed, only locally stored records are read, and each entry carries account_link_id and bank_account_credential_id. It does not mention pagination or result-size behavior.

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?

Two tight sentences with the auth-exemption fact front-loaded, then the resource and the sibling disambiguation. Every clause earns its place.

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 read tool with no output schema, the description supplies the missing pieces: no auth required, data source (our records), and the IDs returned that downstream tools need. An agent has everything required to select and call it.

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?

Zero parameters, so the baseline is 4. The description still names the fields each returned entry carries (account_link_id, bank_account_credential_id), which helps the caller understand the call without any input schema to explain.

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?

States a specific verb (List) and resource (Shinhan Bank account links this caller registered), and explicitly names the sibling it is not — shinhan_easy.accounts.list — by contrasting stored links against live bank fetches.

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?

Gives the when ('reads our records only') and the alternative with its condition ('shinhan_easy.accounts.list fetches live accounts from the bank'), plus the prerequisite that no credential or login is required. Nothing is left to inference.

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