new_context

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

No annotations are present, so the description carries the transparency burden. It does disclose meaningful behavior: the context is isolated and has a separate cookie jar. However, it does not state whether the new context becomes active, what it returns, or how existing contexts are affected.

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?

The description is a single, front-loaded sentence with no filler. Every word contributes to the core purpose, and it is easy to parse quickly.

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?

This tool creates a stateful browser resource, has no output schema, and has no annotations. The description omits critical details such as the return value/context identifier, whether the new context becomes the active one, and the expected shape of the proxy object. An agent cannot fully determine how to chain this with list_contexts or subsequent navigation.

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 100% for the only parameter, proxy, so the baseline is 3. The description adds no extra proxy semantics, and the schema's 'Proxy settings dict' is thin for a nested object, but it remains acceptable for a single optional parameter.

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 clearly uses the verb 'Create' with the resource 'new isolated browser context', and adds a distinguishing detail: 'separate cookie jar'. This makes it easy to identify the tool's function and distinguish it from siblings like list_contexts and get_cookies.

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?

There is no explicit 'use when...' or 'instead of...' guidance. The phrase 'isolated browser context' implies when the tool would be useful, but it does not explain when to choose it over reusing the current context or how it relates to list_contexts/close_browser.

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