Notion Write

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

Despite annotations already flagging destructive behavior, the description goes further by naming exactly which operations (archive, trash, delete) remove content and instructing the agent to confirm with the user. It also discloses response slimming, the verbose:true escape hatch, URL acceptance for IDs, and the error-recovery behavior. This adds significant value beyond the annotations and never contradicts them.

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 compact for the complexity it covers, front-loading the core purpose and destructive warning. It uses bullet-like formatting for the call modes and keeps each sentence informative. It is a bit dense—three paragraphs of dense detail—but there is no filler or repetition; it earns its length.

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 tool with 26 operations, batch support, and no output schema, the description covers every critical aspect an agent needs: the destructive actions, call syntax, response slimming, URL handling, error feedback, and when to consult notion_describe. Nothing essential is missing; it even handles the malformed-payload case to keep the agent on track.

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 is minimal—payload is just an object with propertyNames and additionalProperties, so it conveys almost nothing about the actual shape. The description fills that void by explaining the single vs. batch call modes, the batch-specific fields (items, atomic, idempotency_key, concurrency), and the per-operation markdown strings. It also documents the verbose:true parameter and URL flexibility, all of which the schema omits.

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 precise verb and resource: 'Run one Notion write operation by name.' It immediately distinguishes itself from the sibling tools (notion_read, notion_describe) by framing itself as the write dispatcher, and the long operation enum makes the scope unmistakable.

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 guidance on when to call notion_describe for complex shapes and warns which operations are destructive, requiring user confirmation. However, it never explicitly contrasts with notion_read for reads, so the when-not-to-use instruction is only implied by the tool name rather than stated.

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