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

No annotations exist, so the description carries the burden and does so thoroughly: one upstream request, preservation of native metadata, no auto-paging, no analysis, and explicit return fields (native data, cursor, has_more, log_pb.impr_id). This is rich behavioral disclosure an agent needs to call it correctly.

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?

Four short sentences, front-loaded with purpose, then scope caveats, then return values, then paging instructions. Every sentence carries a distinct fact with no repetition.

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?

Covers purpose, return shape, paging workflow, and limitations without an output schema or annotations. It is close to complete for a search tool, though it could mention result ordering or rate-limit behavior, which an agent might need when iterating pages.

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 schema already documents all four parameters including defaults, ranges, and the search_id dependency. The description reiterates the paging relationship but adds no syntax or format detail beyond what the schema provides, so baseline 3 is appropriate.

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+resource ('Search TikTok sounds by keyword') and distinguishes from siblings by naming sound_videos implicitly and clarifying it is not a trend-growth score. The negative framing ('these are sound search results, not a trend-growth score') is unusually precise about what the tool is not.

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?

Explains the paging workflow (pass impr_id as search_id with returned cursor) and states 'no automatic paging or analysis', giving clear usage context. It does not name an alternative sibling for related tasks (e.g., sound_videos for a sound's videos), so it lacks explicit when-to-use-another-tool guidance.

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