browser_scan

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

With no annotations, the description carries the behavioral disclosure burden. It reveals that the HTML is stripped of scripts, styles, and invisible elements, and that the tool returns a tab list. This adds value beyond the schema but does not mention error handling, permission needs, or whether the tool modifies state (it appears read-only but not confirmed).

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 concise, with a single sentence for the main purpose and a list of arguments. It front-loads the key information. However, the argument list is in a paragraph style; a structured format (e.g., bullet points) would enhance readability without adding length.

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 behavior and output (simplified HTML plus tab list) and mentions the LLM optimization. The presence of an output schema reduces the need to detail return values, but the description is missing edge cases (e.g., behavior when no tabs exist) and does not explicitly state whether the tool is read-only.

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 0%, placing the full burden on the description. The description explains all three parameters ('tabs_only', 'text_only', 'switch_tab_id') with their effects and usage intent. For example, it notes 'tabs_only' saves tokens and 'switch_tab_id' switches tab before scanning. This is strong compensation, though additional details like data types or constraints would improve it.

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 the tool gets simplified HTML content of the active tab plus tab list. The verb 'Get' and resource 'simplified HTML content' are specific. However, it does not explicitly distinguish from sibling tool 'browser_get_tabs', which also deals with tabs. The mention of tab list indicates overlap, but the focus on scanned content differentiates it.

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 provides some usage guidance via the 'tabs_only' argument, implying when to skip page content to save tokens, but lacks explicit when-to-use versus alternatives like 'browser_get_tabs' or 'browser_navigate'. No exclusion criteria or preconditions are stated.

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