export_tracks_to_file

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

Annotations already flag a non-read-only, open-world write; the description adds genuine context the annotations can't: exact destination directory, the YANDEX_MUSIC_EXPORT_DIR override, and the columns written to each format. It omits what happens if file_name already exists (overwrite vs. append) and any behavior for very large libraries.

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 short sentences, front-loaded with the action and output formats, followed by destination and the one conditional requirement. No filler.

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?

An output schema exists, so return values need no explanation, and the description covers formats, destination, and the playlist/kind dependency. The main remaining hole is the semantics of file_name and owner_uid, which an agent cannot infer from any field in the schema.

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 0%, so the description must carry parameter meaning. It explains source (likes vs. playlist) and when kind is required, but file_name and owner_uid are never mentioned, leaving half the parameters undocumented anywhere.

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 (exports all tracks), the resource (likes or a playlist), and the output artifacts (.txt and .csv files on disk). The clause 'не загружая их в чат' directly separates it from chat-returning siblings like get_liked_tracks or get_playlist_tracks.

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?

'не загружая их в чат' gives a clear condition for choosing this over the read-and-return track tools, and 'Для source="playlist" нужен kind' states a prerequisite. It stops short of naming a sibling or stating when not to use it, so not a 5.

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