Hide or unhide a comment

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

Annotations only say non-read-only, destructive, open-world. The description adds material context beyond that: the two-step preview/confirm flow where an unconfirmed call sends nothing, the TikTok capability grant at connection time with explicit reconnect remedy, and the per-platform postId requirement. Those are exactly the operational traits an agent cannot infer from structured fields.

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?

Front-loaded with the core action and its inverse, then platform caveats, then the safety workflow. Dense but every sentence carries necessary information; slight redundancy with the schema on postId and hidden keeps it from a 5.

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?

With 7 parameters, three platforms-specific quirks and an output schema present, the description covers the auth/capability story and the confirmation protocol well enough to call safely. The only unexplained surface is banAuthor's side effect (channel ban), which is implied but not described.

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 100%, so the baseline is 3. The description restates what the schema already documents (hidden: false restores visibility, TikTok/YouTube require postId) and never mentions banAuthor, the YouTube-only author-ban flag, so it adds little beyond structured data.

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 and resource (hide/unhide a comment) plus scope (the profile's own posts) and the exact effect (public no longer sees it, or restored with hidden: false). The multi-platform coverage is enumerated, so an agent can tell at a glance that this is not the same as delete_comment, hold_comment, or approve_comment.

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?

Explicitly routes away from the wrong sibling: 'To delete a comment use delete_comment.' It also defines the required invocation sequence for approval (call without confirmed for a preview, then with confirmed: true) and names the platform precondition (TikTok 'comments' capability, reconnect required). That is when-to-use, when-not, and prerequisites in one place.

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