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

Annotations only declare openWorldHint and destructiveHint=false, but the description adds the traits that actually matter here: a ~40 second sync budget that flips the response from inline posts to a job_id, and that the call consumes credits (pointing to get_account). The async/sync disclosure and credit cost are exactly the operational facts an agent needs before invoking a non-readOnly, open-world search.

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 usage routing, then operational behavior, then scoring semantics — a sensible order for scanning. It is dense and slightly overpacked into one block, and the "2 to 4 specific keywords" point duplicates the keywords field description, but no sentence is wasted.

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 and 8 parameters including 4 enums, the description still covers return shape (post_key per post, or job_id), the meaning of viral_score and the 18+ outlier threshold, and credit consumption. Nothing blocking a correct first 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 coverage is 88%, so the schema does most of the work, but the description adds cross-parameter behavior the schema cannot express: keywords plus window defaults, and that omitting both falls back to the longest recent window (180d TikTok, 365d Instagram/YouTube). The keyword-quality advice (2 to 4 specific terms beat one broad niche) reinforces rather than extends the schema's field description, so it is useful but partly redundant.

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 and resource ("Searches Instagram, TikTok or YouTube for posts that outperformed in the creator's niche") plus the value delivered ("what to borrow from each"). That framing separates it cleanly from list_my_posts, get_feed, and find_competitors without opening a schema.

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 an explicit use case ("find ideas worth remaking") and names the follow-on siblings with their distinct roles: save_inspiration stores, generate_content remix rewrites in the creator's voice. It also routes the async case to get_viral_results and the display case to show_posts, so the agent knows which tool to pick at each step.

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