read

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

Annotations are absent, so the description must carry behavioral disclosure. It reveals some format behavior, but does not disclose that scrollextract/preload variants may scroll, trigger network requests, or change page state, nor does it say anything about return shape or limits.

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 description is compact and front-loads the action plus a format map. The trailing '…' makes the format list feel unfinished, preventing a 5.

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 13 parameters, no output schema, and no annotations, this definition is under-specified. Each format needs its own semantics, scrolling side effects should be flagged, and key parameter interactions should be clarified.

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 62% and there are 13 parameters, so the description must add real meaning. It explains two format values, but leaves selector, goal, summarizeAt, diff, preload, and scrollextract parameters largely to terse schema snippets.

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 definition names a clear verb and resource — 'Read page content' — and gives useful format distinctions ('text' as innerText with offset paging, 'content' as smart SPA extraction). It doesn't explicitly differentiate from sibling tools like explore_page or screenshot, so it isn't a 5.

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?

No when-to-use guidance, no exclusions, and no pointer to alternatives. The format list implies choices, but the description never tells an agent when to prefer read over explore_page, screenshot, or evaluate.

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