view_pages

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

Annotations already declare readOnlyHint=true and idempotentHint=true, so the description does not need to argue safety. It still adds genuinely non-obvious behavior: "Nothing is written to disk," the hard 5-page cap, and the "ask" password mechanism that routes the secret through a local page rather than the chat. The remaining gap is that it never says what form the images come back in or whether non-PDF input_paths are accepted.

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 purpose sentence is front-loaded and each subsequent clause carries a distinct constraint (page limit, pixel range, no disk writes, password handling) with no padding. The run-on placement of the password note at the very end is slightly disjointed from the parameter discussion but does not cost the reader anything.

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 annotations covering safety semantics and an output schema covering the return value, the description need only fill the behavioral and parameter gaps, which it mostly does for a 4-parameter tool. What is missing is the accepted input type (PDF only, or images too), which matters for an agent deciding whether to call convert_to_pdf first.

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%, so the description carries the full burden and largely meets it: it documents the `pages` string syntax with a default and a maximum, the `max_side_px` valid range, default and physical meaning ("the long side of each image"), and the special "ask" value for `password`. Only `input_path` goes undiscussed, and its meaning is self-evident.

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?

"Look at pages as images: layout, scans, charts, signatures, handwriting" states a concrete verb and resource and enumerates the visual content types it is meant for. It does not explicitly differentiate itself from the visually-similar sibling render_pages, so an agent must still guess at the boundary between viewing and rendering.

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 implied by the enumerated content types (charts, signatures, handwriting) — an agent can infer "use this when the answer depends on visual appearance rather than extracted text." However, there is no explicit when-not guidance and no named alternative such as extract_text or render_pages, so choosing between visual and textual inspection is left to inference.

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