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

Annotations establish idempotent/non-read-only safety, but the description adds critical behavior beyond them: partial merge semantics, strict per-type validation, draft-only revision for published pages, and the publish/unpublish workflow constraints. No contradiction with 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 description is long but not padded; every sentence carries either merge semantics, validation behavior, or high-stakes publishing workflow. The core action is front-loaded before the caveats.

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?

The description covers the key behavioral and sequencing facts, and an output schema exists so returns need not be described. The only notable gap is editToken, which appears in the schema with no description anywhere and isn't explained in the tool description.

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 high, so the baseline is 3, but the description adds useful meaning: props are 'merged into existing props' and blockId is stable. The 'and/or a new type' phrasing is slightly imprecise because type is required by the schema, though the variant descriptions clarify that current type should be passed unless changing it.

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 description opens with a specific verb and resource: 'Patch one content block by stable blockId.' It immediately distinguishes block_update from sibling block_add/block_delete/block_reorder and names the two inputs that matter (props patch and type change).

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 when-not guidance: for already-published pages it only saves an unpublished revision, and it instructs not to call page_publish in the same turn, to wait for a separate user request, and not to call page_unpublish. This is exactly the kind of cross-tool sequencing an agent needs.

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