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

With no annotations provided, the description carries the full burden of behavioral disclosure. It discloses several non-obvious behaviors: results have atomically associated material_reference without standalone IDs, exposure is global lifetime estimated exposure (not country-specific), pagination reports has_more rather than an exact total, and query uses concept matching rather than exact text matching. It also warns against repeated paging. This is strong behavioral transparency, though it doesn't cover every edge case (e.g., error behavior, rate limits).

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?

The description is dense but well-organized: it front-loads the core purpose, then packs critical behavioral caveats into compact sentences. Every sentence earns its place — the country_match semantics, exposure scope, pagination behavior, and the explicit exclusion of visual-description search are all high-value. It's slightly long, but given 21 parameters and no annotations, the density is justified.

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 21-parameter search tool with no annotations and no output schema, the description covers the most important contextual gaps: result identity model, pagination semantics, exposure scope, country matching semantics, and the unsupported search type. It doesn't describe the return shape in detail, but with no output schema and a complex tool, the description does a solid job of covering what an agent needs to know to call it correctly. Minor gaps remain around error cases and rate limits.

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 baseline is 3. The description adds meaningful semantic context beyond the schema: it explains that country_match 'contains' matches any country while 'exclusive' requires exact set equality, clarifies that exposure is global lifetime estimated exposure, and notes that query uses concept matching expanded to Chinese source labels. It also warns that video_type is mutually exclusive with material_type/material_types. This goes beyond the schema's per-parameter descriptions.

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 opens with a specific verb ('Discover') and enumerates the full set of filter dimensions (games, countries, platforms, formats, languages, aspect ratio, duration, device, quality, discovery dates), which clearly distinguishes it from sibling search tools. It also explicitly states what results contain (material_reference, no standalone creative/ad IDs), further differentiating it from tools like get_material_detail_v2 or search_materials_by_filter.

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?

The description gives explicit routing guidance: use get_game_platform_stats for totals instead of repeated paging, and states that arbitrary visual-description semantic search is not supported (which routes away from this tool for that use case). It also clarifies country_match semantics (contains vs exclusive) and pagination behavior (has_more, not exact total), giving an agent clear conditions for when and how to use this tool.

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