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

Annotations already cover read-only/idempotent safety, and the description goes well beyond them: the scoring basis (likes, comments, shares, saves, short-link clicks; views as fallback), the lift scale (2 = twice as good), the statistical thresholds (8 measured posts, 3 per side, 25% difference), the 'missing' field for shortfalls, and the causal caveat ('these go together with results, they don't prove cause: try a finding and check again'). This is unusually informative about how results are produced and how to read them.

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?

Dense but largely earning its place: traits list, then what each finding contains, then methodology, then thresholds, then the caveat and sibling routing. The opening enumeration of traits is long and slightly overwhelms the front position, but nothing is truly redundant and the important constraints sit in readable single sentences.

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 carries the full burden and does so: it enumerates the returned fields (trait, better/worse, lift, post counts per side, plain-language advice), the additional outputs (trend, top_posts) and the 'missing' signal. Combined with the read-only annotations and fully described parameters, an agent has what it needs to call and interpret it.

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 every parameter carries its own description, so the schema does the heavy lifting. The description adds no detail about days, group_ids, channel_ids or workspace_id beyond the implicit 'each account's' scoping. Baseline 3 applies.

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 makes clear this returns per-account findings about post traits (format, text length, hashtags, timing) that correlate with better or worse results, plus trend and top_posts. It distinguishes itself from siblings by naming get_analytics (numbers) and get_best_times (hours). The opening clause 'What went with each account's better and worse posts' is awkwardly phrased and less direct than the title 'What worked', but the body pins the resource down.

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?

Explicit routing: 'Use it before writing the next posts; get_analytics has the numbers, get_best_times the hours.' It also states a hard precondition ('Needs 8 measured posts') and a per-finding precondition (3 posts per side, 25% difference), which implicitly covers when the tool is not useful. No explicit statement of when to skip it entirely, but the context is clear.

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