Start browser session

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

Annotations only provide readOnlyHint=false and openWorldHint=true, which are minimal. The description adds meaningful behavioral context: the session persists, has an idle timeout, and carries state across calls. This goes beyond the annotations and helps the agent understand the side effects (creating a session) and its lifecycle. It does not cover failure modes or cleanup details, but that's acceptable for a start tool.

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?

Two sentences with no redundant words. The primary function and the critical session-lifecycle detail are front-loaded. Every phrase earns its place; no filler or vague language.

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 start tool with 7 parameters and no output schema, the description provides the essential return value (sessionId) and the session semantics. An agent would know how to initiate a session and that the session persists. Minor missing details: how long the idle timeout is, and whether the session can be reused across different browser contexts, but these are not critical for correct invocation.

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 71%, so most parameters (url, model, baseUrl, headless, userAgent, viewport) have meaningful schema descriptions. The tool description does not add extra parameter context, but that's acceptable given the schema's richness. The baseline of 3 is appropriate since the description adds no additional parameter-level value beyond what the schema already provides.

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 the specific action ('Opens a new browser session') and the key output (returns sessionId). This clearly distinguishes it from siblings like browser_navigate or browser_snapshot, which operate within an existing session. The purpose is unambiguous and action-oriented.

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?

The description explains the session's persistence ('stays alive across tool calls until closed or idle-timed-out') and implies this is the entry point for browser interactions. It does not explicitly state when not to use it (e.g., 'if you already have a sessionId, skip this'), but the context is clear enough for an agent to infer that. A small enhancement would be to mention that this should only be called once per interaction flow.

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