Search TikTok music

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

Annotations already declare readOnlyHint=true and destructiveHint=false, and the description adds substantial behavior beyond that: the fundamental limitation (searches cached trending charts, not the full catalogue), matching semantics (case- and accent-insensitive, every word must match), and the note that TikTok has no search endpoint. This is exactly the kind of non-obvious behavioral disclosure an agent needs.

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 (~200 words) but every sentence earns its place: purpose, downstream id usage, the critical catalogue limitation, matching rules, and capability prerequisite. The most important information is front-loaded and the critical caveat is prominently marked with 'IMPORTANT'. Slightly longer than minimal, but the complexity of the tool justifies the length.

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?

Given 6 parameters, an output schema, and safety annotations, the description covers the tricky parts: limitations, matching behavior, downstream integration, and prerequisites. The only minor gap is that the 'omit q to get the trending chart' behavior lives in the schema rather than the description, and the overlap with tiktok_music_trending is implied rather than addressed directly. This is nevertheless very complete for an agent to call correctly.

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 value on top by explaining the chart-scoped semantics of genre/country/period interplay ("widening the search means trying another genre, country or period") and matching rules that qualify how q behaves. This is meaningful but modest compensation beyond an already well-documented schema.

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 uses a specific verb and resource: "Find a TikTok Commercial Music Library track by song title or artist, to soundtrack a TikTok video." It also distinguishes the tool from a naive search expectation by explicitly stating it does NOT search TikTok's whole catalogue, which separates it from sibling tools like tiktok_music_trending.

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 strong usage context: how to pass the returned id downstream ("as tiktokMusicId in upload_video's platformOptions, not commercial_music_id"), how to widen a failed search ("trying another genre, country or period"), and the capability prerequisite ("declare the music capability"). It does not explicitly name the sibling alternative tiktok_music_trending or give a when-not-to-use statement, so it falls just short of a 5.

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