web_console_messagesConsole output captured from the DESKTOP grid browser page (by pageId) since it opened, including page errors. Buffered from load — nothing is lost by asking late. NOT a device — for a real phone or tablet use android_devtools_console_logs or ios_safari_console_logs (by udid).
| Name | Required | Description | Default |
|---|---|---|---|
| filter | No | Case-insensitive substring filter, e.g. "error" | |
| pageId | Yes | Page ID from web_navigate |
Changes observed during successful MCP inspections.
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnly/idempotent/non-destructive, so the safety profile is covered. The description adds real behavioral context beyond that: output is buffered from page load and nothing is lost by querying late, and page errors are included. It doesn't cover ordering or truncation, but it clearly exceeds the annotation baseline.
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 tight sentences, front-loaded with what the tool returns, then the buffering guarantee, then the disambiguation. No filler; each sentence carries distinct information.
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 read-only retrieval tool with no output schema, the description covers what is returned (console output and page errors), the retention behavior (buffered since load), and the scope boundary versus device alternatives. Nothing an agent needs to call it correctly is missing.
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 both parameters (pageId, filter) are already documented in the schema, establishing the baseline of 3. The description only reinforces pageId scoping and mentions errors indirectly; it adds no syntax or semantics for the filter parameter beyond what the schema 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?
States a specific verb+resource: console output from the DESKTOP grid browser page, keyed by pageId, including page errors. It explicitly contrasts itself with the android/ios console-log siblings, so an agent can distinguish it from nearby tools without opening a 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?
Gives an explicit when-not clause ("NOT a device") and names the exact alternatives to use instead for phones/tablets (android_devtools_console_logs, ios_safari_console_logs, by udid). The condition selecting this tool versus those is unambiguous.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.