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

Annotations already cover the safety profile (readOnlyHint=true, openWorldHint=false), and the description adds real context beyond that: daily refresh cadence, default outlier filtering, best-ratio-first ordering, freshness tied to last_checked_at, and the niches_used/niche_note response fields. However, it does not describe pagination behavior or result volume, so it adds useful but not rich behavioral disclosure.

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 core purpose and scope, and the dense single paragraph packs defaults, niche resolution, and next steps. It is slightly overstuffed — the scheduling call-to-action sentence is more product guidance than tool guidance — but nothing 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?

For a 12-parameter, zero-required read tool with no output schema, it covers what matters: default niche resolution, outlier default, ordering, and freshness of numbers. The only gap is that it never hints at result shape or pagination, which an agent would otherwise infer from page/limit alone.

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%, so baseline is 3, but the description earns more by defining the ratio sort metric and, crucially, explaining the interaction between q, niche, category, and all_niches (the fallback to the user's setup category and how niches_used reports it). That interplay is not obvious from the per-parameter descriptions alone.

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?

States a specific verb+resource: 'Find what is trending' in 'Sendhour's viral library of public TikTok posts and YouTube Shorts', and defines the core concept precisely (ratio = views ÷ the account's usual views). This clearly separates it from sibling tools like list_videos or find_slide_photos, which surface posts without viral-outlier ranking.

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?

Explicitly describes the default retrieval mode when no q/niche/category is given, names list_niches as the alternative for picking another niche, and states the downstream workflow (find formats/hooks/sounds, then make your own version and schedule it). It also gives an inclusion condition (outliers only by default) that tells the agent when to deviate.

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