browser_console_messages

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

The free-text adds almost no behavioral nuance beyond what annotations already provide. It does not mention the default scope of 'after navigation' versus 'from the session start' (controlled by the 'all' flag), nor the possibility of saving to a file rather than returning text. The sentence simply restates the resource name without additional procedural insight.

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?

The one-sentence description is extremely concise and free of unnecessary wording, front-loading the main idea efficiently. It could be longer, but as a brief summary it is appropriately structured and not bloated.

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?

The tool's behavior is actually nuanced—console messages can be filtered by severity level and can be limited to the current page. The description fails to explain the return format ( text or file) or the existence of these parameters/capabilities. Without supplemental information from the schema, an agent might assume 'all' means all severities whereas only retrieving info-level messages by default is the actual outcome.

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?

The input schema provides complete descriptions for all 3 parameters and covers 100% of them, so the baseline is adequate. The description adds no extra meaning about level filtering, filename handling, or the interaction between 'all' and 'level'; it does not conflict but also does not compensate beyond the 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?

The description states a specific resource ('console messages') and a specific action ('Returns'), and the tool name confirms this. It can be clearly distinguished from sibling tools like browser_network_requests or browser_snapshot, which address different browser features. However, the word 'all' is slightly misleading because the level parameter actually filters output.

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?

There is no guidance about when to use this tool versus alternatives, nor any mention of typical use cases, prerequisites, or exclusions. The description only states the core product and does nothing to route an agent to the correct selection between this and related browser tools.

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