previous_page

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

No annotations are provided, so the description carries the full burden. It discloses the key behavioral context that this drives the user's real Chrome browser via an extension, and that scrolling can target the document or a single element, which is useful. However it says nothing about scroll magnitude (viewport vs. full page), whether it blocks, or any auth/permission requirements.

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?

Front-loaded guidance in brackets followed by two tight sentences describing the action and default. The preamble is somewhat verbose but earns its place by stating the real-browser constraint; no filler beyond that.

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 no-output, low-risk scroll tool with both parameters documented, the description supplies what an agent needs to invoke it correctly. The only residual gap is the ambiguity of 'previous page' (viewport scroll vs. paginated content), which slightly weakens completeness against the next_page sibling.

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 coverage is 100%, so the baseline would be 3, but the description adds real meaning by explaining the default behavior of the index parameter (whole document when omitted) that the terse schema does not convey. It leaves the 'intent' parameter meaning entirely to the schema, hence not a 5.

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 specific verb and resource ('Scroll the document in the window or an element to the previous page') and scopes the fallback ('if no index is specified, scroll the whole document'). It is distinguishable from siblings like next_page or scroll_to_top by its direction, though it never explicitly contrasts itself with them.

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 bracketed preamble gives a clear use condition: 'use only when the task requires acting on a real website,' which implicitly excludes non-browser or mocked contexts. It provides context for selection but names no specific alternative sibling (e.g., next_page or scroll_to_percent) the agent should pick instead.

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