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

Annotations already declare readOnlyHint=true, openWorldHint=true, idempotentHint=false and destructiveHint=false, so the safety profile is covered. The description adds a genuinely useful behavioral fact the annotations lack: 'Costs 1 credit per call'. It stops short of explaining non-idempotency or result variability across repeated calls.

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?

Two tight sentences, purpose front-loaded with the cost caveat trailing. No filler or redundancy.

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?

There is no output schema, so the description carries some burden for explaining what comes back; it hints at scored signals/hooks/angles but not the shape or per-ad granularity. Cost and purpose are covered, making it minimally adequate but not rich.

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?

With 60% schema description coverage, the description is expected to compensate, but it only restates 'keywords' which the schema already documents well. The undocumented parameters (max_queries, active_status) receive no explanation of defaults, limits, or semantics from the prose.

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 and resource ('Scrape public Meta Ad Library by keywords') plus the value-add ('score winning signals, hooks and angles'). The Meta-specific framing cleanly separates it from sibling ad_radar_tiktok_top and from the balance/evaluate utilities.

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?

Usage is implied by the keyword-search framing, but there is no explicit when-to-use or when-not guidance and no routing to siblings such as ad_radar_evaluate or ad_radar_tiktok_top. An agent must infer the platform boundary on its own.

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