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

Far beyond the annotations: it names exactly what gets overwritten (settings, terms, pages), how menus merge (differing label/parent adds beside the old item and is noted), what is never touched (deletion, deactivation, deactivated structure not in the blueprint), which sections are advisory-only and reported blocked, that writes go through ordinary tools so their permissions and token scope apply, and that on_error 'stop' keeps writes already made. The 'never deletes' wording is reconciled with destructiveHint=true by the explicit overwrite list, so this is clarification rather than contradiction.

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?

Purpose and the dry-run default are correctly front-loaded, and nearly every clause carries real information (unwritten_fields, not_written, notes). However it is delivered as one dense paragraph of semicolon-chained clauses that forces re-reading to separate refusals from outcomes, so structure costs it more than the length does.

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?

For a 9-parameter, nested-object, destructive tool with no output schema, the description covers the failure modes (refused rows, truncated sections, blocked sections, max_writes, on_error), the reporting keys an agent will see back (unwritten_fields, not_written, notes, unchanged), and the permission boundary. Nothing needed to call it correctly is missing.

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 100%, so the baseline is 3; the description earns an extra point by explaining consequences the schema does not, notably that settings always exist so a settings apply writes nothing without update_existing, and that max_writes exhaustion explains why a re-run still has work. It says nothing about session, expect_hash or allow_partial beyond what the schema already states, which caps it short of 5.

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 first clause gives a specific verb and resource ('apply the applicable parts of a blueprint to this site') and immediately positions itself relative to a named sibling ('the write side of wp_blueprint_diff'). An agent can distinguish it from wp_blueprint_diff, wp_blueprint_export and the individual wp_create_*/wp_update_* tools without opening a schema.

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 states the default mode (dry run without apply=true), when to escalate to writes (update_existing), and explicitly routes the read-only planning case to wp_blueprint_diff via the shared plan_hash. It also explains the repeat-run case ('writes only what earlier runs left undone') so an agent knows re-invocation is safe rather than duplicative.

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