Post a new comment on the brand’s own TikTok post

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

Annotations carry readOnlyHint=false, openWorldHint=true, destructiveHint=false. The description adds significant behavior beyond these: TikTok silently hides spam comments with no error signal, the raw-URL refusal on a new comment (vs. replies), and the verification loop. No contradiction — a write operation aligns with readOnlyHint=false. The silent-failure disclosure is exactly the kind of external behavior annotations cannot express.

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?

Dense but front-loaded: core action and constraints first, then the image flow, then the critical silent-spam warning, then auth. Every sentence earns its place for a tool with this complexity. Minor detraction is the heavy all-caps emphasis (TIKTOK SILENTLY HIDES, NEEDS THE TIKTOK ACCOUNT AUTHORIZATION), which is stylistically loud but does flag genuine risks.

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?

Complete for a write tool with five parameters, a cross-tool upload dependency, a silent-failure mode, and an auth gate. The description covers the action, input constraints, the prerequisite upload flow, how to verify success (read-back), and the auth requirement. No output schema exists, but the description's note about the absence of failure signals effectively documents the response semantics.

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 schema already documents all five parameters — baseline 3 applies. The description adds marginal value: it clarifies videoId refers to an owned post and stresses passing imageUri+imageWidth+imageHeight 'together,' but the schema's 'required with imageUri' and 'raw URL is NOT accepted' already carry most of that weight. The description does not need to compensate for a coverage gap.

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 precise verb-resource pair — 'Write a NEW top-level comment on a TikTok post the authorized account owns.' It distinguishes itself from both reply_to_tiktok_comment (explicitly noting a reply is the one place a plain URL is accepted) and post_to_tiktok, so an agent can disambiguate without opening other schemas.

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?

Extensive and explicit guidance: the text-or-image requirement, the mandatory pre-upload via upload_tiktok_comment_image, the contrast against reply behavior, the read-back verification method via list_tiktok_comments, and the auth prerequisite pointing to tiktok_account_status. It leaves nothing to inference and directly steers toward the correct sibling tools.

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