Comments

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

Annotations declare openWorldHint and non-idempotent but leave the mixed read/write nature and deletion semantics opaque. The description supplies the important gaps: the API does not return resolved threads, added comments are removed via notion_undo, and an integration can only delete its own comments.

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?

One tight paragraph, front-loaded with the action breakdown before the format and lifecycle notes. Every clause carries information; nothing is repeated from the schema or name.

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 no-output-schema mutation/read tool with 5 params, the description covers the return shape for list (open comments plus discussion ids) and the write lifecycle. Pagination via `limit` and the exact add/reply response shape are unstated, but the essentials for correct invocation are present.

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?

With schema coverage at 60%, the description compensates by explaining that `text` is markdown with bold/links/mention syntax (a concrete example format the schema lacks) and by tying `discussion_id` to action=list. It adds real meaning beyond the field descriptions.

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 opening verb triad ('Read, add, or reply to comments') names both the resource and each operation, and then disambiguates the three actions line by line. An agent can distinguish this from notion_insert_blocks or notion_patch_block without opening the 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?

It specifies the condition selecting each action (list for a page/block's open comments, add to start a discussion, reply to answer by discussion_id) and routes removal to notion_undo. It stops short of stating when to prefer this over other comment-adjacent siblings, but the action-level guidance is clear.

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