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

Annotations declare destructiveHint=true and idempotentHint=true, and the description usefully explains the destructive mechanism ('Replaces that box's version if it exists') and the auth modes (signed-in vs claim_token), which is context beyond the booleans. It does not describe failure modes or what happens when the melody has errors.

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 sentences, front-loaded with the core action, then the replacement rule, then the auth scope and precondition. No wasted words; every sentence carries distinct information.

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?

With an output schema present, return values need no explanation, and the description covers action, replacement, auth, and the melody-validity precondition. Only minor gaps remain (error behavior, relationship to validate_melody).

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 already 83%, so the baseline is 3, but the description adds real meaning by spelling out the box dimension ('15, 20, 30 notes or freestyle') and the one-version-per-box constraint. It reinforces rather than merely restates the schema.

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: 'Saves a melody as the version of an existing song for one box.' It also scopes the cardinality rule (one version per box) and the replacement behavior, which distinguishes it from siblings like create_song and fit_melody_to_box.

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 clear context for when it applies: the signed-in person's songs, or an account-less song via claim_token, plus the prerequisite that the melody must have no errors. It does not name explicit alternatives (e.g. validate_melody as the fix path), so it stops short of full when/when-not routing.

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