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

Annotations only declare readOnly=false, openWorld, non-idempotent, non-destructive; the description adds the material facts an agent needs — billing (paid per piece charged to the key's Gisoo credit, USD cost returned in text), latency (~1 minute), and the exact return format (base64 MP3 audio block). That is real disclosure beyond structured fields.

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 the verb and output, then cost and latency — well ordered. The Persian sentence largely duplicates the English content, which is a small amount of redundancy but not harmful padding.

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?

No output schema exists, yet the description tells the agent what comes back (base64 MP3 audio block) and what the call costs in time and money. With only 2 params and full schema coverage, nothing an agent needs to invoke 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%, so both parameters are already documented in structured form; the description merely restates prompt content categories and the default model. It adds 'optional lyrics', which the schema already covers, and no length or formatting guidance beyond maxLength.

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 ('Compose one short piece of music from a description') plus the output form (MCP audio block, base64 MP3), which cleanly separates it from siblings like create_video, generate_image and text_to_speech. Scope ('one short piece') is explicit.

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 selection context: short clip, default model lyria-3-clip-preview, roughly a minute, and it is paid — enough to decide between this and other media tools. It never explicitly excludes anything or names a sibling as the alternative when a longer track is needed.

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