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

Annotations already cover the safety profile (readOnly, non-destructive, open-world), and the description adds genuine context on top: the return envelope for list actions ({ results, next_cursor, next }) versus single-item returns for post and profile, the fact that a page may hold fewer items than count, and a 24-hour cursor lifetime. That last detail is a real operational constraint an agent could not infer from annotations or schema.

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 purpose, then per-action contracts, then pagination semantics and the cursor TTL — a logical order with no filler. Density is high but every clause carries operational information, and the tool's seven-action surface justifies the 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?

Given 10 parameters, 7 actions, no output schema, and no nested objects, this is the amount of description needed and it delivers. Return shapes are described even though no output schema exists, and pagination plus cursor expiry are fully covered. Nothing an agent needs to invoke this correctly appears to be missing.

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 already 100%, so the baseline is 3; the description earns above that by binding each parameter to its action ('post (id)', 'comments (video_id; optional count, cursor)'), which the flat schema cannot express on its own. It also clarifies that cursor must be sent back 'unchanged' from the same action and target. It doesn't add formatting or validation detail beyond the schema, so not a 5.

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?

Opens with a specific verb+resource ('Read public TikTok data') and immediately explains the tool's routing model: one tool, an action discriminator, and per-action arguments. Each of the seven actions is then enumerated with its required and optional inputs, so an agent knows exactly what the tool covers without opening the schema. The platform scope also cleanly separates it from x-search, instagram and facebook siblings.

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?

Gives clear routing guidance among actions (use search for keyword videos, post for one video by ID, profile_posts for a user's videos, etc.) and an explicit chaining rule: 'A video id from search can be passed to post or comments.' Pagination usage is spelled out precisely. It stops short of naming when to prefer a sibling tool or platform, and there are no explicit exclusions, so it lands at 4 rather than 5.

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