browser_console_messages

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

Annotations already declare readOnlyHint=true, destructiveHint=false and openWorldHint=true, so safety is covered structurally. The description adds nothing beyond that — no note about the default lookback window, the level cascade behavior, or that output may be written to a file instead of returned inline.

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?

A single five-word sentence is maximally concise and front-loaded, but here brevity comes at the cost of accuracy and utility rather than earned economy. There is no wasted sentence, but there is also almost no content.

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 4-parameter tool with no output schema, the description omits the return format (text vs. saved file) and the scope defaults that determine what the agent actually receives. The misleading word 'all' makes the gap worse, since an agent could reasonably expect a full-session dump by default.

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 schema fully documents 'all', 'level', 'filename' and 'sessionId', including the level cascade and the default lookback window. The description contributes no additional parameter meaning, so the baseline of 3 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 clear verb and resource ('Returns all console messages'), so the agent knows it reads console output. However, 'all' is inaccurate: the schema shows the default returns only messages since the last navigation and only levels at or above the requested severity. It also does not distinguish itself from the sibling browser_network_requests.

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?

No guidance on when to reach for this tool versus browser_network_requests, browser_evaluate, or browser_snapshot. There is no mention of prerequisites such as having an active page or session, and no exclusions.

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