Start Manual Registration Session

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

Adds access constraints (Beta, invite-only), explains that this starts a browser the user can watch and drive via an authenticated viewer_url, and clarifies that agent-driven navigation is not part of this call. The annotations already signal mutating/open-world behavior, and the description adds live-viewer semantics without contradicting them. It could mention session lifecycle or cleanup, but this is substantial added context.

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 sentences, front-loaded with the essential start action and deliverable, followed by routing guidance and a pairing tip. There is no filler or repetition of schema fields. The first sentence is dense and could be parsed more cleanly, but each sentence 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 9-parameter tool with no output schema, the description covers the core purpose, output link, and relationship to create_order, but leaves gaps around session lifecycle, how to use viewer_url, and the semantics of attach vs fresh mode. Those gaps matter for correct invocation, so the description is adequate but not fully complete.

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?

The input schema covers all 9 parameters with descriptions and enums, so the baseline is 3. The description enriches 'country' with country-matched proxy logic and hints at order_id relevance via optional order phone number and timeline, but it does not explain mode attach/fresh, run_prep, or prep_preset beyond the schema. Thus it offers only a small increment over the structured data.

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?

The description states a specific action—starting a country-matched cloud browser for manual takeover—and names the key deliverable, viewer_url. It also distinguishes itself from agent-driven navigation tools and positions itself relative to create_order. There is no ambiguity about what this tool does.

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?

Clearly frames manual takeover as the intended use case and tells the agent that agent-driven navigation belongs to separate opt-in session tools, establishing a when-to-use boundary. Pairing guidance with create_order gives a concrete invocation context. However, it does not name the session sibling tools explicitly or explain attach vs fresh selection, so the guidance is strong but not exhaustive.

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