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

Annotations already declare readOnly/idempotent/non-destructive, yet the description still adds real behavior: results come from the user's own posts rather than general advice, the data is an estimate, the 5-post minimum with a graceful fallback explaining how to test, and 'Free and read only; it schedules nothing.' That last line preempts a plausible misreading that the tool would act on its advice.

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 the trigger and the answer shape, then scope, then exclusions, then the safety note. Example phrasings do real work for matching, and no sentence is redundant.

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?

Output schema exists so return values need no explanation; the description instead covers what an agent actually needs: data source, method, estimation caveat, minimum-data threshold, defaults, and neighbor tools. Nothing material is missing for a two-param read-only tool.

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 0%, so the description carries the full burden and mostly does: it documents timezone as an IANA name with UTC default, and platform as 'one platform or all'. The only gap is that the accepted platform value vocabulary (e.g. tiktok/youtube) is never spelled out, and the schema has no enum to fall back on.

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?

Names a specific question the tool answers and grounds it with concrete user phrasings ('best time to post on TikTok', 'when should I upload my Shorts'), then states the actual computation: average views 24 hours after posting by weekday and 4-hour block. That distinguishes it clearly from analytics siblings like get_post_stats or weekly_report.

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 explicit triggering conditions plus an explicit 'Not for:' list naming the alternative tools (plan_posts, draft_post, weekly_report) and the situations each covers. An agent can route without inferring anything.

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