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

Annotations already declare readOnlyHint=true, destructiveHint=false and openWorldHint=false, so the safety profile is covered. The description adds one genuine behavioral fact beyond the annotations — that the data is cached rather than freshly pulled — but says nothing about staleness, refresh behavior, or the tenant-scoping requirement.

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?

It is a single front-loaded sentence with no filler, which is efficient. But for a 9-parameter tool it is under-specified rather than genuinely concise, and the phrase "read-only MCP surface" is internal jargon that spends words without informing the agent.

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 9 undocumented parameters, no output schema, and a rich set of sibling insight tools, the description omits everything an agent needs: what the overview returns, how grouping/sorting/dates shape it, and when to prefer it over live-query siblings. Only the read-only safety profile is adequately covered, and that comes from the annotations.

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?

The schema has 9 parameters at 0% description coverage, including date_from/date_to, search, group_by, sort_key/sort_dir, and pagination fields. The description mentions none of them, so it does nothing to compensate for the complete absence of schema documentation on filter, grouping, or paging semantics.

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 specific verb and resource ("Read ... cached TikTok insight overview") and the word "cached" hints at a distinction from live pulls. However, it never differentiates itself from the many sibling insight tools (insights_query_overview, insights_query_batch_overview, insights_pull_insights), so an agent cannot tell which one to pick from the description alone.

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?

There is no explicit when-to-use guidance, no conditions selecting this tool over the sibling insight queries, and no mention of prerequisites. The only contextual signal is the vague phrase "without leaving the read-only MCP surface," which does not route the agent to a correct choice.

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