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

The description goes beyond the annotations (destructiveHint=true, idempotentHint=true) by explaining the behavioral consequence: 'For already-published pages, this saves an unpublished latest revision only.' It also discloses the expected workflow around stopping and telling the user the draft/preview was updated, and waiting for explicit permission to publish. This is rich behavioral context that annotations alone do not convey.

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 a single paragraph that front-loads the action in the first sentence, then provides necessary warnings and workflow steps. It is somewhat long, but every sentence earns its place given the critical constraints about publishing. It could be tightened into bullets, but it is well-structured and not wasteful.

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?

Given the tool's destructive nature and interaction with publishing, the description covers the operation's effect, prerequisite lookup via page.get, the published-page revision behavior, prohibitions on publishing/unpublishing in the same turn, and the expected user interaction. An output schema exists to handle return values, so no further description is needed. This is thorough for the tool's complexity.

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 0%, so the description must compensate. It clarifies that blockId is a 'stable' identifier and implies pageId can be obtained via page.get, but it does not explain the optional editToken parameter or explicitly define pageId's role. This partial compensation is better than nothing, but leaves some gaps for a 3-parameter tool.

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 'Delete one block by stable blockId,' which is a specific verb plus resource and clearly distinguishes this from sibling block tools like block.add, block.update, and block.reorder. It also adds the nuanced behavior about published pages saving an unpublished latest revision, further clarifying the tool's scope.

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?

Explicit usage guidance is provided: 'Use page.get first if unsure which id to remove' tells the agent when to call another tool first. It also gives explicit exclusions—'Do not call page.publish in the same assistant turn' and 'Do NOT call page.unpublish either'—and instructs to wait for a separate user message before publishing. This is clear, actionable guidance with alternatives and exclusions.

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