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

Annotations already declare the write profile (readOnly=false, destructive=false, idempotent=false), so the bar is lower; the description still adds real context: project-scoping that ignores the active-project pointer, the returned project identity, and exactly which music-item fields get solved. It omits any mention of the dry_run preview flag and idempotency nuances, which are the notable remaining gaps.

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 scoping and WRITE markers are correctly front-loaded, but the body is a single semicolon-chained sentence mixing four parameters, making it hard to parse. Every clause is informative, but the structure prioritizes density over readability.

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 9-parameter mutation with no output schema and very low schema coverage, the description covers the musical intent but leaves four parameters undocumented and the return shape only vaguely stated ('project identity with its result'). Adequate to call it, incomplete for confident use.

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 only 11% (project_id alone), so the description must carry the load and does so partially: it explains payoff, hold_s, intro_filter, and stutter_at. It says nothing about music_id, dry_run, stutter_beats, or stutter_slice (the two enum slices 1/8 and 1/16), leaving key controls unexplained.

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 and resource ('shape_music' / 'bend the user's track') and is explicit that it edits the music item's offset/start/end/fades so a payoff lands on a drop. It is clearly a timing/shaping mutation rather than add/remove/swap music, though the phrasing ('bend the user's track to the story') is idiomatic and takes a beat to decode.

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 scoping condition ('User tracks only') and per-parameter intent, which implies when the tool applies, but never names or contrasts with close siblings such as set_music_fit, swap_music, add_music, or plan_to_music. The agent must infer the alternative from the sibling list rather than the description.

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