inspect

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

The description adds significant behavioral context beyond the annotations (readOnlyHint, destructiveHint). It explains the network capture lifecycle ('auto-starts capture on first call, dumps on subsequent'), which is non-obvious. It also clarifies conditional requirements for selector. No contradictions with annotations.

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 a single paragraph that efficiently conveys the tool's purpose and behavior. It front-loads the main action and lists targets with brief explanations. Every sentence adds necessary information; there is no redundancy. A bulleted list could improve scannability, but the current structure is adequate.

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 description covers the main use cases and targets well, but it does not mention the return format or structure of results. Given the absence of an output schema, the agent might need to infer what each target returns. Additionally, it does not address error handling or relationships to sibling tools, leaving some gaps.

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 already covers 100% of parameters with descriptions. The description adds value by explaining the enum values in context (e.g., what each target does) and clarifying the conditional usage of selector (required for element, optional for dom). This goes beyond the schema's 'What to inspect' for target.

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 clearly states 'Inspect the current page' and then elaborates with specific targets (page, dom, a11y, element, network), each with a distinct purpose. This verb+resource specificity distinguishes it from siblings and leaves no ambiguity about what the tool does.

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 explains when to use each target (e.g., 'requires selector' for element, 'auto-starts capture' for network) and provides a default. While it does not explicitly mention when not to use the tool versus siblings, the context of a read-only inspect tool is clear from annotations and the description itself.

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