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

The readOnlyHint annotation already covers the safety profile, and the description layers on real behavioral detail: errors are capped at the latest 10 distinct entries, versions are returned newest first, and reading defaults to the live version. It stops short of noting size limits or pagination for the code payload, but adds meaningful context beyond the annotations.

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 summary is front-loaded and each sentence earns its place, with the return shape kept in a separate tag rather than bloating the prose. The description is somewhat longer than strictly necessary, but the structured split keeps it scannable.

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 an accurate description of the return object was essential, and the <returns> block covers field names and ordering for errors and versions. Combined with the before/after-read workflow guidance, an agent has everything needed to call and interpret this tool.

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 100%, so all three parameters, including on_behalf_of, are already documented in the schema. The description's <returns> block implicitly clarifies the distinction between the 'version' parameter and the returned live_version, but adds no new syntax or constraints for the parameters themselves, so the baseline 3 applies.

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 summary opens with a concrete verb and resource ('Read a page's code') and enumerates exactly what comes back: code, version history, and reported browser errors for that version. That is clearly distinguishable from siblings such as list_pages, update_page, create_page, and restore_page_version.

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 explicit workflow guidance: read before changing a page, and again after a change once someone has opened it, with the rationale that errors show what broke. It does not name a when-not condition or explicitly contrast with restore_page_version/get_node_history, so it falls just short of a full routing statement.

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