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

Annotations already cover the safety profile (readOnly, non-destructive, idempotent, openWorld), so the description's job is to add context, and it does: it discloses the transcription fallback logic ('actual video openings when possible, else caption openings') and the caching side effect ('results persist on the leads for 24h'). The persistence note is a state change not implied by readOnlyHint, but it is a benign caching side effect of an analysis tool rather than an outright contradiction of the read-only claim.

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?

Three dense sentences, front-loaded with the core computation, then the usage question, then the persistence caveat. No restatement of the name or title, and every clause carries information an agent would otherwise have to infer.

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 9-parameter, zero-required, no-output-schema tool, the description adequately explains what comes back (ranked per-creator virality plus top videos with captions and hooks) and when to reach for it. It omits prerequisite state (that kept leads must already exist) and any cost/latency warning for the transcription path, small but real gaps for a tool that can transcribe video.

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 description coverage is 100%, so every parameter already carries its own documentation (defaults, caps, enum meanings, uid/token fallbacks), which sets the baseline at 3. The description adds meaning only at the aggregate level — it explains the virality formula and what 'top videos' contain — without illuminating any individual parameter beyond the schema.

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 chain of operations (fetch posts → compute virality as max views vs followers → rank → return top videos with captions/hooks) on a specific resource set (kept creators). The 'kept creators' scope and the virality metric readily separate it from siblings such as analyze_seed_creators, find_viral_trends, and discover_creators.

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 usage trigger with a natural-language example ('which of my creators have the most viral videos and what hooks do they use'), which is stronger than implied usage. It stops short of naming alternatives or exclusions — there is no statement like 'use analyze_seed_creators for non-kept creators' — so it lands at clear-context-but-no-exclusions.

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