login

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

With no annotations, the description carries the full burden and does well: it discloses that the browser is non-headless (human interaction required), that the call blocks until login succeeds or the timeout elapses, that state is saved even on timeout, and that state is keyed by domain and isolated per session. It omits where the credentials land on disk and whether an existing valid login is overwritten.

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 one-line action summary, then the operational context, then per-argument notes. Slightly repetitive between the opening line and the second paragraph, but every clause carries information an agent needs.

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 no explanation, and the description covers the rest of what matters for a side-effecting, human-in-the-loop tool: interaction model, timeout behavior, and state keying. Nothing essential to invoking it correctly is missing.

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 must compensate, and it does: url is 'any page of the target site, keyed by domain', timeout is seconds waited with state still saved on expiry, and session is a namespace for parallel identities that web_fetch must match. That is real semantics — particularly the domain keying and the session must-match rule — not present in 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 action chain — open a headed browser, let the user log in manually, persist the resulting cookies to disk — and anchors it to a concrete sibling trigger (web_fetch returning login_required=true). An agent can distinguish this from session_list/session_export without reading any 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?

Gives an explicit activation condition: use it for sites where web_fetch reports login_required=true. It also explains the multi-account case via distinct session names. It stops short of saying when NOT to use it (e.g. checking existing state with session_list first, or that it is unnecessary when a session is already valid).

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