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

Annotations already declare idempotent, non-destructive, closed-world behavior, so the bar is lower; the description adds real operational facts beyond them — output formats, 180 s cap, loop/cue/stem outputs, a 2-hour link expiry, and an acceptable-use URL. It stops short of explaining failure modes (e.g., what happens if the song check fails) or the exact return payload.

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?

Front-loaded with the triggering condition and tightly packed with no filler sentences; the trailing agent-instruction ('Reply in 1-2 sentences plus the file') and link-expiry/AUP note are somewhat dense but each carries usable information. Slightly overloaded with parenthetical enumerations but still efficient.

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 13-parameter, nested-object tool with no output schema, the description covers intent, format/duration constraints, output artifacts (files, links valid 2 h), and the mtl-vs-compose path. Gaps remain around minor flags (zip, genre, loudness, detail) and no explicit statement of the response shape beyond 'the file'.

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 77% and already documents len, format, style, loop, cues, stems, mtl, and compose in detail. The description only summarizes 'WAV, Ogg or Opus; up to 180 s, loops, cues, stems' at a headline level and says nothing about the undocumented params (zip, genre, loudness, detail, cue). Baseline 3 applies since the schema carries most of the semantic load.

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 (render a song to audio) plus the output formats and duration cap, and frames the user intent (music, song, jingle, soundtrack). It is clearly distinguishable from siblings like sfx (effects), song (composition/checking), and convert.

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?

Explicit about when to use ('when the user wants ... as audio') and how to route: send mtl or compose, and 'render checks the song itself, so skip song first' directly rules out a preceding song call. Alternatives (mtl vs compose) are named with a pointer to describe for generators.

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