login_begin

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

With no annotations, the description carries the burden and does well: it discloses the credential-handling prohibition and that behavior forks on display availability (visible Chrome vs headless via 'ahb login-view'). It leaves unstated whether the call blocks/waits for the human, how long, and what happens on timeout or a second invocation.

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?

Three short sentences with the core action and the safety constraint front-loaded, followed by the environment-specific caveat and the follow-up step. No redundant restatement of the tool name, no filler.

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 tool with an output schema (so return values needn't be described) and no annotations, the description covers action, safety, environment variance, and the next step. The remaining gap is lifecycle detail — blocking behavior and failure modes — which matters for a human-in-the-loop tool.

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 no per-argument semantics are required; baseline 4 applies. The absence of parameters is itself consistent with a tool that merely opens a page.

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 — 'Open the Google sign-in page for a human' — which is concrete and unambiguous. It also implicitly separates itself from login_finish by saying to call that afterward, though it never explicitly contrasts the two beyond sequencing.

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 ordering guidance ('Call login_finish afterwards') and a hard constraint on agent behavior ('The agent must never type credentials'), which tells the agent exactly what role it plays. It doesn't state when this tool should be avoided (e.g., if already signed in) or how to recover from a failed/abandoned login.

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