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

Annotations already mark this as destructive and idempotent, but the description adds critical behavioral detail: for already-published pages, the tool 'saves an unpublished latest revision only' and leaves the live page public. It also clearly warns against publishing or unpublishing in the same turn offers safety context beyond the annotations. There is 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 front-loaded with the core action and the stable-blockId detail. The subsequent sentences are long but each carries important safety and workflow context. It is somewhat verbose, especially the multi-clause instruction about waiting for a separate user message, but that verbosity is justified given the risk of accidentally modifying a live page.

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 primary deletion behavior, the published-page revision behavior, and important sequencing constraints. An output schema exists, so the return value does not need to be explained. However, editToken is left completely unexplained in both the schema and the description, and the behavior for unpublished pages is only implied. These gaps mean an agent may not know when to supply editToken or what exactly happens in the non-published case.

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?

The input schema provides no descriptions for pageId, blockId, or editToken, and schema description coverage is 0%. The description only clarifies that blockId is stable and suggests page_get when unsure. It does not explain the role of editToken, why pageId is needed, or any constraints around them. The description does not adequately compensate for the missing schema-level parameter documentation.

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 exactly what the tool does: 'Delete one block by stable blockId.' The verb is specific, the resource is clear (a single block), and it is easily distinguished from siblings like block_add, block_update, and block_reorder. The mention of 'stable blockId' also clarifies the type of identifier used.

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?

Explicitly tells the agent to call page_get first if unsure which block to remove. It also gives clear rules about not calling page_publish in the same assistant turn, waiting for an explicit user request to publish, and avoiding page_unpublish unless the user explicitly asks to take the page down. This is strong, unambiguous routing and sequencing guidance.

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