Front-page picks

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

Annotations already declare readOnlyHint, idempotentHint, openWorldHint and destructiveHint=false, so safety and idempotency are covered. The description adds genuinely non-obvious behavior: results are editorial/curated rather than metric-driven, and returned refs are designed to be chained into vod_title. It stops short of describing pagination or how many rows come back per site.

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 sentences, front-loaded with the resource and scope, then the use case, then the routing alternatives. The parenthetical row list is compact and informative rather than padding; nothing is redundant with the annotations or schema.

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 does the necessary work of sketching the return shape (per-site rows, slider, list) and the ref-chaining path onward, and all three params are covered by schema descriptions. It could be slightly more complete about row counts or what 'both' returns in terms of volume, but nothing essential for a correct 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 description coverage is 100%, so the enum meanings for kind and site and the per_row bounds are already fully documented. The description only indirectly reinforces parameter behavior by describing which rows exist per site, which adds little beyond the schema text. Baseline 3 applies when the schema carries the semantic load.

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 verb+resource ('Show what Filimo and Namava promote right now') and enumerates the exact surfaces returned (Filimo front-page rows: new, popular, box office, genres; Namava top slider and top list). It also explicitly distinguishes the content type — 'editorial picks, not view counts' — which separates it from sibling tools like vod_search or vod_collection.

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 ('what is popular / trending on Filimo or Namava') plus two named alternatives with conditions: vod_title for details from a ref, and vod_collection(key="namava:popular") for Namava's most-viewed list. That is close to textbook when/when-not routing, with only a mild unaddressed overlap with the vod_new sibling for the 'new' row.

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