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

Annotations declare the safety profile (not read-only, not destructive, not idempotent). The description adds genuine context beyond them: media is a separate upload step, and idempotency_key is the mechanism to avoid duplicate tracks on retry, which usefully explains the idempotentHint=false setting rather than contradicting it.

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, each earning its place: what it creates, what it deliberately omits, and the retry-safety mechanism. The scope boundary is front-loaded before the optional advice.

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 mutation tool with no output schema, the description covers the key behavioral facts and the schema covers all parameters. The main omission is the prerequisite workflow — that field names come from get_requirements — which is only surfaced inside the nested schema, not in the description.

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 coverage is 100%, so artist, fields, dry_run, and idempotency_key are all documented in the schema, including the get_requirements linkage for field names. The description adds no syntax or format detail beyond 'pass idempotency_key if you might retry', so the baseline 3 applies.

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 ('Create a track') and immediately bounds the scope by excluding audio and cover art, which distinguishes it from sibling tools like update_track, set_track_artists, and request_upload. An agent can tell what this tool does and does not own without opening any schema.

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?

Gives a clear conditional trigger for idempotency_key ('if you might retry') and implies the media-upload path belongs elsewhere. It stops short of naming alternatives explicitly (e.g. 'for audio/art use request_upload', 'to modify an existing track use update_track'), so no exclusion guidance is present.

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