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

Annotations already declare readOnlyHint=true, destructiveHint=false, openWorldHint=false, so the safety profile is covered. The description adds real behavioral context beyond that: v3 pages are refused, access is owner-scoped, and a paid plan is required. It doesn't cover the response size or whether the whole tree is always returned untruncated, so it stops short of a 5.

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?

Three sentences, front-loaded with the core read action and its return contents, followed by the workflow alternative and eligibility caveats. Dense with parentheticals but nearly every clause carries information; only the repeated version notation ("4.0") is slightly redundant.

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, so the description must carry return shape — and it does, naming the top-level fields and every element type in the tree. Combined with the write-back partner, version gating, and access requirements, an agent has everything needed to call it correctly.

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 67% and the schema itself documents pageId, pageIndex, and their default/fallback relationship. The description adds no parameter-level detail at all — it never mentions pageId, pageIndex, or projectId, so it neither compensates for the undocumented projectId nor clarifies the pageId/pageIndex precedence. Baseline 3 for schema-driven coverage.

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 (read) and resource (a v4 page document), then enumerates exactly what the document contains (width/height, languages, fonts, element tree with box/text/image/svg/device/flow). This clearly differentiates it from siblings that also touch pages, such as render_screenshot or generate_page.

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?

Explicitly pairs it with set_page_document for the modify-and-write-back workflow, and states the eligibility conditions: only v4 projects (create_project version "4.0"), a v3 page is refused, owner-scoped, paid plans. An agent knows both when to call it and when it will fail.

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