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

Annotations already declare readOnly, idempotent, non-destructive, so the safety profile is covered; the description adds value beyond that by disclosing the return shape ('play link plus quiet notes'), the cost model ('free score check: check:true'), and an agent-facing workflow rule ('Fix problems silently; tell only the user_summary'). The term 'quiet notes' and 'user_summary' are not defined anywhere, which keeps this from a 5.

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, front-loaded with the triggering condition, with no filler. The final fragment 'Free score check: check:true' is terse to the point of being cryptic, but every sentence carries 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 9 params, a nested compose object, and no output schema, the description still manages to state the return value (play link plus notes), the cost of the check mode, and the intended agent behavior on failure. Gaps remain around what 'quiet notes' contain and what a failing check looks like, but nothing critical to calling it correctly is missing.

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 description coverage is 100%, including enums and the nested compose object, so the schema already carries the parameter burden and baseline 3 applies. The description only adds a cost hint for check:true and the no-audio guarantee; it adds nothing about mtl vs compose selection beyond what the schema's describe(topic=...) pointers already say.

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 action (check an MTL song or compose spec) with an explicit scope qualifier (no audio generated). It also distinguishes itself from the render sibling by noting render performs the same check. The generic tool name 'song' is rescued by the description rather than the other way around.

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 want an MTL song or compose spec checked with no audio' gives a clear triggering condition, and '(not needed before render, which checks it too)' names the sibling and the case where this tool is redundant. No guidance is offered relative to describe, convert, or sfx, but the primary ambiguity is resolved.

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