browser_settings

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

The annotations only declare that this is a non-read-only, non-idempotent, open-world call. The description goes well beyond them: it discloses that the call blocks until the user saves or closes the window, that the timeout is 10 minutes, that the agent never sees the credentials, and that they are stored encrypted — all essential for planning around a human-in-the-loop tool. It also explains the certificate-trust side effect, which no annotation covers.

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?

Front-loaded with the trigger condition, then a short per-parameter block, with no filler sentences. The hard-wrapped bullet formatting makes it slightly harder to scan than it needs to be, but every line contributes information.

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?

An output schema exists, so return values need not be covered, and annotations already establish the safety profile. What is left for the description — blocking duration, credential confidentiality, profile/url interplay, certificate trust — is all present, making the definition sufficient to call 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 description coverage is 0%, so the description carries the full load, and it does: it explains that `profile` is the target saved login, that supplying `url` auto-creates a login when the profile does not exist, and that `url` scopes the password to one exact site. The remaining gap is that all parameters are optional (0 required), yet the description never says what happens if both are omitted.

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?

Names a concrete action (open a window where the USER types credentials) and a concrete trigger set (HTTP Basic/NTLM browser sign-in boxes, self-signed certificates). That said, it never names the obvious siblings (start_login, complete_login, save_session), so an agent must infer that this handles browser-native auth rather than form logins by reasoning from the trigger description alone.

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 a clear, specific context for when to call it — intranets, routers, old admin pages, self-signed certs — plus a useful branch for the case where no saved profile exists yet. It stops short of an explicit exclusion rule ("for ordinary form logins use start_login instead"), so the when-not-to-use side is left implicit.

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