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

Beyond the readOnlyHint and openWorldHint annotations, the description discloses extensive behavioral specifics: it never starts transcription, breakdown lists are sorted and capped at 1000, status values are explained (available_bounded, partial, unavailable), copy_language statuses are detailed, and media URLs are intentionally excluded. There is no contradiction with annotations.

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?

Though lengthy, the description is densely packed with essential details and every sentence serves a purpose. It is logically ordered: core fields, language specifics, breakdown behavior, id source, media exclusion, and quota. No fluff or repetition, and the most critical purpose is front-loaded.

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 tool with this many status codes, edge cases, and output nuances, the description leaves nothing critical uncovered. It explains all breakdown statuses, language copy statuses, sorting/capping behavior, and the quota, making it sufficient for an agent to call correctly without opening the output schema. Complete.

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?

The schema describes the id as 'the resource id to fetch' with 100% coverage. The description adds crucial semantics: the id is a creative UUID from search_creatives and the same id is used for get_media, providing provenance and cross-tool linkage that the schema alone lacks. This elevates it above the baseline.

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 clearly states the tool fetches one creative's metadata and its bounded breakdown by id, listing specific fields like activity period, languages, and aggregates. It differentiates itself from siblings by noting the id comes from search_creatives and that media URLs are handled by get_media, making its purpose distinct and unambiguous.

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 provides clear context for when to use this tool: when you need detailed creative metadata by UUID, especially from search_creatives. It also points to get_media for downloading media and mentions that fanpage ids feed other search filters, giving practical guidance. However, it doesn't explicitly state scenarios where one should NOT use this tool over alternatives, leaving some inference to the agent.

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