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

Annotations only supply readOnly/idempotent/non-destructive; the description goes well beyond them by enumerating the result vocabulary (create, update, unchanged, extra_on_target, advisory, blocked), stating there is no delete mode, that extra_on_target is never touched by apply, and that blocked sections occur when underlying tools are off or out of token scope. It also explains plan_hash staleness refusal and the multi-site forwarding caveat.

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?

Front-loaded with the verb, the target and the read-only guarantee in the first two clauses. It is long and clause-dense, but nearly every sentence carries operational information (result categories, no delete mode, hash staleness, token scope) rather than filler.

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 no output schema, the description carries the full burden of describing the return value and does so exhaustively, including the meaning of plan_hash and per-category results. Nothing an agent needs to interpret or safely chain the call 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 description coverage is 100%, so the schema already documents session, sections, blueprint and allow_partial in detail. The description only adds provenance for blueprint ('from wp_blueprint_export on this or another site'), which is helpful but marginal against a fully documented schema; 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?

States a specific verb and resource ('Compare a blueprint ... against the CURRENT state of this site') plus the exact output intent ('return exactly what wp_blueprint_apply would do'). It also names its two siblings (wp_blueprint_export as the blueprint source, wp_blueprint_apply as the consumer), so an agent can place it in the workflow 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?

Establishes the use case (dry-run preview before applying) and a key operating condition: it works whether or not wp_blueprint_apply is available, and plan_hash is fed to apply as expect_hash. It does not state an explicit 'do not use this when…' exclusion, but the export → diff → apply routing is clear enough to act on.

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