Import a saved login

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

Annotations only mark it non-readonly/destructive/non-idempotent; the description adds the real behavioral context: local-server-only, it blocks waiting on the person (up to 2 minutes default), Chrome shows an approval prompt, and it replaces any existing login for the domain. It also pre-empts a security concern by stating the response never contains a cookie or stored value.

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?

Dense but front-loaded: the purpose and effect land in the first clause, then prerequisites, then the return shape. The semicolon-chained sentences are information-rich, though the return-field enumeration ('...') is slightly loose and could be tightened.

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?

With no output schema, the description still describes the return shape (domain, savedAt, cookieCount, localStorage, sessionSha256) and what it never returns. Prerequisites, timeout, approval flow, and replace-on-conflict semantics cover everything needed to invoke it 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?

Schema coverage is 0%, so the description carries the full burden and does: 'site' is defined as a domain or a page URL on it, and 'approveTimeoutMs' is explained as the Chrome approval wait with a stated default of 120000. Both of the two parameters gain meaning absent from the schema.

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 and resource (save the person's login to a site) and immediately names the downstream effect ('so mode authed reads its pages signed in as them'), which separates it from list_logins and remove_login at a glance. The scope detail (domain or page URL) is concrete rather than tautological.

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 clear conditional context: the person must be signed in to Chrome's default profile with remote debugging on, and the agent must 'ask the person first and name the site'. It also supplies a when-not rule ('a site a page led you to is not theirs to save'). It stops short of explicitly naming sibling alternatives, so 4 rather than 5.

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