page_layout

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

No annotations are provided, so the description carries the full burden, and it does substantial work: it discloses that results are numbered, in reading order, and that coordinates are in page units with bbox format [x0, y0, x1, y1]. It stops short of explaining the effects of image/scale or the exact response structure (JSON items vs. rendered image).

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?

Two short paragraphs, front-loaded with what the tool returns before the workflow guidance, and no filler. The coordinate example ('a check at x1 + 20, (y0 + y1) / 2') is dense but earns its place by making the placement math unambiguous.

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?

With no annotations, no output schema, and 0% schema coverage on four parameters, the description should explain more. It covers the return semantics and cross-tool workflow well, but leaves the meaning of path, page, and scale entirely to inference, which is a real gap for an agent invoking it the first time.

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% across four parameters, so the description must compensate and largely doesn't. It never explains path (the notebook file), page (default 1), or scale (default 0.9); only the image parameter is indirectly hinted at via 'read the numbered image'. The bbox/coordinate explanation is useful but describes output semantics rather than the inputs.

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 names the resource precisely (the page's ink) and specifies the output shape: numbered items of words/phrases per line, bounding boxes in page units, in reading order. That level of detail lets an agent distinguish it from siblings like page_ink, page_marks, and render_page without opening the schema.

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?

It gives an explicit use case and the alternative it precedes: 'Use it before write_on_page to aim marks', then walks through the concrete workflow of reading the numbered image and placing a check relative to a bbox. It doesn't say when NOT to use it, and doesn't clarify the boundary against overlapping siblings like page_ink or page_marks.

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