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

Beyond the annotations, it discloses the 1-credit cost, the asynchronous nature of the job, host-dependent MCP Apps progress-card behavior, and the fallback polling path with the songId. These are exactly the operational traits an agent needs and that structured fields do not carry.

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-loads purpose and cost, then the lyrics workflow, then polling behavior. Efficient, but the sentences are long and densely packed with conditional clauses, which slightly hurts scannability.

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?

Covers cost, approval workflow, async progress handling and the polling fallback, and an output schema exists so return values need not be described. Nothing needed to invoke or manage the call 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%, so title, style and lyrics are already fully documented. The description restates the lyrics-omission semantics (instrumental) but adds no syntax or format detail beyond the schema, so the baseline 3 applies.

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 ('Make a new song') plus the exact inputs (title, style, lyrics) and the conditional scope (no lyrics makes an instrumental). An agent can distinguish this from generate_remix/reimagine_song without opening any schema.

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 an explicit workflow: write the lyrics yourself with part tags unless the user supplied words or wants an instrumental, show them, and only generate once approved. It also states when to poll (get_song_details) versus when the host handles progress, so both branches are covered.

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