Call a page or DevTools tool

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

Annotations already declare readOnlyHint=false and openWorldHint=true, so the mutation/open-world profile is known. The description goes beyond them with genuinely additive context: WebMCP tools are site-supplied code and their output is untrusted ('the site's word'), and CONSEQUENTIAL ones can place orders, payments, or messages. It stops short of timeout/error semantics or how to handle a consequential prompt.

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: the action and its argument source come first, then a compact risk disclosure. Every clause earns its place and nothing is repeated from the schema or annotations.

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?

No output schema exists, and the description does cover the nature of returns (untrusted site-authored output) without describing their shape. For an open-world dispatcher this is close to complete; it lacks only notes on call failure/timeout behavior, which the timeoutMs parameter implies but never explains.

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%, so the baseline is 3. The description adds real value by pointing the agent at browser_tool_schema as the source of truth for the 'arguments' object, which the schema itself only refers to abstractly as 'the tool's input schema'.

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 (runs/calls a tool) plus the exact resource class (a tool from browser_list_tools) and the execution target (the session's page). It names the two sibling tools in the discovery flow, so an agent can distinguish it from browser_list_tools and browser_tool_schema without opening any schema.

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 implies the intended workflow (list tools, read schema, then call) and flags the condition that matters most: tools marked CONSEQUENTIAL take real actions. It does not, however, say when to prefer this dispatcher over siblings like browser_evaluate or run_task, nor any explicit when-not-to-use case.

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