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

Annotations already declare readOnlyHint, idempotentHint, and destructiveHint=false, so safety is covered structurally. The description adds genuine behavioral context beyond that: the comparison baseline is 'since the last build' and the scope spans pages, site pages, and settings — telling the agent exactly what universe of objects is examined. It does not cover pagination or result ordering, keeping it below 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?

Two compact sentences with no filler. The definition of what is returned comes first and the usage instruction second, so the agent gets purpose before procedure.

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?

No output schema exists, but the description compensates by enumerating what the result contains (every page, site page, and setting changed since the last build). For a low-complexity single-parameter read tool with full annotations, the definition is nearly complete; only the exact result shape (counts, per-item fields) is left implicit.

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?

There is only one parameter and schema description coverage is 100% ('Site id (dsite_…)'), so the schema fully carries parameter documentation. The description adds no format or scoping detail about the site argument, which is acceptable at the baseline for a single fully-documented parameter.

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 and resource: what the next publish would change on a site, enumerating the three entity classes (page, site page, setting) changed since the last build. That is clearly distinguishable from siblings like get_build_status, list_pages, or get_site_settings, which report state rather than delta.

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?

Gives explicit when-to-use guidance ('Read it before publish_site') plus the intended follow-through ('tell the person what will go live'). No alternative tool is named as a substitute, but the pre-publish precondition is stated directly and leaves little to infer.

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