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

Annotations already establish a safe read-only, idempotent operation, yet the description adds substantial context the annotations cannot: refresh cadence ('every few hours, often in a post's first day'), attribution rule (a post counts in the period it was published, with its latest numbers), and per-network measurement gaps including the explicit by_network.measured=false / coverage.notes signal. That is exactly the caveat-level disclosure this dimension rewards.

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 correctly: metrics and breakdowns first, then freshness, then the caveats, then use cases and filters. The network-caveat parenthetical about LinkedIn/TikTok is dense and back-loaded, but each clause carries real behavioral information rather than restating the schema.

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?

There is no output schema, so the description must carry the return shape itself — and it does: totals with prior-period comparison, day-by-day, by network, by account, top posts, and the null/measured-flag conventions. For a six-parameter read tool this is as complete as an agent needs to call it and interpret the response.

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% and each parameter is self-documented, so the baseline is 3; the description earns above baseline by explaining the period semantics that give from/to their meaning (the previous comparison window is 'the same length', and posts are attributed by publication date). It does not explain how the 'top' posts are ranked or selected, which is the one semantic the schema leaves open.

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 names the exact resource (a workspace's posts over a period) and enumerates every metric returned — views, reach, likes, comments, shares, saves, engagement, engagement rate, link clicks, followers — plus the comparison and breakdown dimensions. It also explicitly separates itself from the sibling get_post, which shows one post at a time with nulls for unreported numbers.

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?

It gives concrete use cases ('what worked this week', choosing best time or format, client reporting) and routes single-post lookups to get_post. What it lacks is a clear when-NOT-to-use or a statement about which sibling to pick for other reporting needs (e.g. list_posts vs this), so the agent must still infer some routing.

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