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

Annotations already declare readOnly/idempotent/non-destructive, and the description adds genuinely new behavior: conversion is lossy for .mtk and share links because "cues and macros are compiled away", and file-based formats are base64 in both directions. It doesn't flag other lossy round-trip risks (e.g. MIDI losing tracker-specific data) or size limits, which the schema alone covers.

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?

Two sentences, front-loaded with the usage trigger, then the format list, then the lossy-conversion caveat. Every clause carries information an agent needs; nothing is repeated from the schema.

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 3-required-param, no-output-schema tool, the description covers valid formats, encoding convention, and lossiness, which is most of what's needed. It stops short of saying what the response looks like (converted text vs base64 payload vs link string) for each target format.

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?

Only 33% schema coverage, but `from`/`to` are self-describing enums and the description explains what each format label actually means (MTL text, .mtk file, share link, tracker modules), plus the base64 and read/write convention that applies to file formats. The only remaining gap is not spelling out base64 explicitly per direction (input vs returned output).

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 ("move a song between") and enumerates every supported source/target format (MTL text, .mtk, share link, MIDI, MOD/XM/S3M/IT), which matches the from/to enums exactly. No sibling tool (assets, describe, render, sfx, song) performs conversion, so the boundary is 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?

"Use this when you need to move a song between..." gives a clear triggering condition for the tool. It does not name when NOT to use it or point to an alternative sibling (e.g. song vs convert), but the niche is narrow enough that the context is sufficient.

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