update_toggle

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

With no annotations provided, the description carries the full burden of behavioral disclosure, and it excels. It openly states the destructive nature, no rollback, that child block IDs change, and the risk of partial emptying on mid-call failure. It explains server-side handling of API limits (batching, splitting, nested passes) and clarifies that markdown becomes native blocks, not plain text. It also details the dry-run behavior and return structure. This is far beyond minimal transparency.

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 lengthy but every sentence earns its place given the tool's complexity. It opens with the critical destructive warning, then states the core purpose, then details behavior, limits, and response. It is well-organized, flows logically, and avoids redundancy. The density of information is appropriate for a tool with this many nuances, and there is no fluff.

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, API limit handling, markdown-to-native-block conversion, and multiple return scenarios (including dry run), the description covers all essential aspects. It explains what changes, how failures affect state, how to create a restore point, what the server does automatically, and the exact response shape. No output schema exists, so the description's detailed return documentation is crucial, and it provides it comprehensively.

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 complete descriptions for all six parameters (coverage 100%), so the baseline is 3. The description adds extra meaning primarily for the 'markdown' parameter—clarifying it is replacement body content, not a wrapper, and that the server converts it to native Notion blocks. It also clarifies the effect of 'collapse_soft_wraps' under specific scenarios. This goes beyond the schema's short descriptions and justifies a 4.

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 states a specific verb and resource: 'Update the body of one toggle by title from a page.' It clearly delineates scope by specifying it matches plain toggle blocks and toggleable heading_1/2/3 blocks, and distinguishes itself from siblings like replace_content by clarifying it updates a toggle's body, not renaming it or acting as a wrapper. The wording is unambiguous and directly relatable to the tool's name.

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?

While the description does not explicitly name alternative tools like replace_content or update_section, it provides rich context on when to use it: it targets a specific toggle by title, handles nested structures, and automates API limit batching. The warning about destructiveness and the recommendation to duplicate_page for irreplaceable content implicitly conveys when caution is needed. It lacks explicit 'when not to use' exclusions, but the context is strong enough for an agent to infer appropriate usage.

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