page_marks

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

With no annotations, the description carries the full burden, and it does disclose meaningful behavior: tape states ("covered" hides content, "revealed" was tapped open), the 12-crop cap, and that crops reveal tapes. It never states error behavior for a bad path, permissions, or that this is a read-only operation.

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 summary sentence followed by labeled blocks for highlights, tapes, and crops — no filler. Slightly dense prose, but each clause adds information an agent needs.

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?

There is no output schema and no annotations, so the description must describe the return shape; it does this reasonably (regions with colour and bbox, tapes with bbox and state). The gap is the undocumented path parameter, which is required to call the tool at all.

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 0%, so the description must compensate for all three params. It adds real meaning for crops (zoomed region crops, max 12, tapes revealed) and page (1-based), but says nothing about path, the required parameter, leaving the most important argument undocumented.

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?

"Highlighter and tape marks of a page (1-based)" names a specific resource and content type that is clearly distinct from sibling extractors like page_ink and page_layout. It stops short of explicitly contrasting itself with those siblings, but an agent can tell what it retrieves.

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?

Usage is only implied — the agent must infer that this is the tool to call when it needs existing highlights/tape regions. It does route to render_page/render_region with reveal_tapes=True for hidden content, which is a useful alternative pointer, but no when-not-to-use condition is stated.

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