notion_delete_blocks

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

With no annotations, the description carries the full burden and does well: it discloses the dry-run preview behavior, that text blocks are serialized to a local deletion log while child pages/databases go to Notion Trash, and that shared workspaces require an extra opt-in plus user confirmation. It does not say what happens to other block types (images, embeds) or whether deletion cascades to nested children, which leaves the destructiveness profile partly open.

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?

Four short sentences, front-loaded with the action and then the safety semantics; nearly every clause carries operational meaning. Slightly dense run-on phrasing in the last clause ('only after the user said yes') costs a little precision but not readability.

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 mutation tool with no annotations and no output schema, the description covers the critical unknowns: preview mode, where deleted content goes, how to restore, and the shared-workspace authorization gate. It stops short of describing the preview response shape or the fate of non-text blocks, which an agent would still have to discover by calling it.

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 only 25%, so the description must compensate, and it does for three of four parameters: confirm (preview gate), allow_shared (guest/shared workspaces), and block_ids (targets by id). Only 'page' is covered by the schema itself, and no parameter is left fully unexplained.

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+resource ('Delete blocks by id') with the id-based targeting that distinguishes it from page-level siblings. It also names the two restore counterparts, so an agent can place it in the tool family without opening any 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?

Gives explicit conditional guidance: without confirm:true it only previews, and guest/shared workspaces need allow_shared:true gated on user consent. It names notion_restore_blocks and notion_restore_page as the recovery paths. The one gap is that it never contrasts this with notion_trash_page, leaving the delete-blocks-vs-trash-page choice to inference.

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