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

Annotations already cover the read-only safety profile (readOnlyHint=true) and external reach (openWorldHint=true), so the bar is lower. The description adds genuinely behavioral detail not in the annotations: omitting videoIds silently returns the most recent posts, and the call is scoped to at most 20 posts. It does not say what happens if more than 20 ids are passed (error vs truncation) or describe pagination.

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?

Two sentences, no filler, and the return contents are front-loaded ahead of the parameter guidance. Every clause carries information the agent needs.

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 no output schema, the description usefully compensates by enumerating the metric categories that come back and by stating the per-post scope and 20-post cap. Minor gaps remain around over-limit behavior and whether results are ordered or paginated, but nothing essential to making the call is 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 description coverage is 100%, so the baseline is 3 and the schema already documents videoIds format and the accountId/profileId provenance. The description still adds value by explaining the omit-videoIds default and pointing to list_posts as the id source, which the schema does not state.

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 concrete verb and resource ('Return counters and watch metrics') and enumerates the exact metric families (watch time, full-watch rate, retention, impression sources, audience), which unambiguously separates it from the account-level get_tiktok_account_insights. It does not explicitly name which sibling to use instead, so it stops short of full sibling differentiation.

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 actionable invocation context: 'videoIds is a comma-separated list of post ids from list_posts' tells the agent where ids come from, and 'omit it for the most recent posts' defines the default path when no ids are supplied. No explicit when-not-to-use or alternative-tool routing (e.g. vs get_tiktok_account_insights for account-level data) is given.

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