Create Browser Session

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

Goes well beyond the annotations by disclosing the credential flow (logs in, proves cookies work standalone), the artifact's location and permissions (0600, owner-only, in the server's session directory), and that the returned value is a path and never the cookies. It also adds a crucial safety disclosure the annotations cannot express: the session carries the user's full UI rights outside the server's change policy, plus handling instructions not to print, read out, or commit the file.

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 action and artifact, then layered with safety and cleanup instructions in a logical order. It is dense and long for a two-parameter tool, but nearly every clause carries operational or safety value, with only mild redundancy between the 'never the cookies' and 'never print/read out' statements.

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?

With no output schema, the description still specifies the return value (the storage-state file path). It covers auth source, storage location and permissions, gating condition, and cleanup, which is everything needed to invoke a destructive, open-world session-minting tool 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 coverage is 100%, and the schema already explains the instance alias, env-var fallback, and the name pattern. The description only echoes 'for an instance alias' without adding naming conventions or fallback behavior beyond the schema, so the baseline applies.

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 precise verb and artifact: 'Mint a verified Playwright browser session for an instance alias', and anchors it to a known reference ('as nex auth browser-session does'). The pairing with the sibling delete_browser_session makes the lifecycle boundary unambiguous.

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 explicit preconditions ('refused when changes are not permitted') and a clear follow-up action ('delete it with delete_browser_session when the browser work is done'), which routes the agent to the correct sibling. It stops short of describing when a browser session is preferable to other auth approaches, but the when-to-use context is otherwise clear.

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