browser_full_audit

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

No annotations are provided, so the description carries full responsibility. It thoroughly details what the tool returns (nine error categories with diagnostics) and implies it is a read-only audit (no mention of side effects). However, it does not explicitly confirm that it modifies no state, nor does it discuss permissions, rate limits, or destructive potential. The absence of annotations puts more burden on the description, and while it discloses the output structure well, it leaves some behavioral traits unstated.

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 description is well-structured into two paragraphs: the first provides the purpose and error sources, the second lists the return structure as a bullet-like list. It is front-loaded with the key action and scope. While slightly verbose (listing all nine return fields), each sentence adds value by clarifying what the tool captures. No redundancy, but could be trimmed slightly.

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?

Given the tool's complexity (aggregating nine error types) and the absence of an output schema, the description provides a comprehensive breakdown of the return structure with clear categories. It also specifies the usage context (after page load or interaction) and the default behavior for `since`. This fully compensates for the missing output schema, making the tool's behavior and results predictable for an agent.

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?

Input schema coverage is 100% (both parameters have descriptions in the schema). The tool description does not add extra meaning beyond what the schema already provides; it does not elaborate on when to use `since` or `includeWarnings`. Since schema_description_coverage is high, a baseline of 3 is appropriate. The description adds no value beyond the schema for parameter semantics.

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 begins with a specific verb '执行全量错误审计' (perform full error audit) and clearly identifies the resource as '当前页面' (current page). It then enumerates all aggregated error sources (CDP console, injected scripts, network 4xx/5xx, etc.), which unambiguously defines the tool's scope. This level of specificity distinguishes it from sibling tools like browser_errors_aggregate (likely a lighter aggregation) and browser_click_audit (focus on click interactions).

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 explicitly states when to use the tool: '在页面加载完成后或交互操作后' (after page load or interaction). It provides clear context for appropriate invocation. However, it does not mention cases where the tool should not be used (e.g., if only specific error types are needed) or explicitly compare against alternatives like browser_errors_aggregate. Nonetheless, the guidance is practical and sufficient for most use cases.

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