suno_cover

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

No annotations exist, so the description carries the behavioral disclosure burden. It adds two useful facts: 'Costs credits' (financial/monetary consequence) and 'Returns task_id' (implies asynchronous execution). However, it stops short of telling the agent what to do with the task_id (e.g., poll suno_wait/suno_poll), and it does not disclose failure/refund behavior or that credits are consumed even on failure. It adds some value but leaves the async contract half-explained.

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?

Four terse sentences, each adding a distinct fact (purpose, personaId, credits, return type). The structure is efficient and front-loaded. However, for a 14-parameter tool with no annotations, this level of brevity crosses from conciseness into under-specification; important workflow and parameter information is omitted in the name of shortness.

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?

Given the high complexity (14 params, 1 required, no output schema, no annotations), the description is materially incomplete. It explains the purpose and the task_id return but does not establish the end-to-end flow (upload → cover → poll → download), document the meaning of most parameters, or clarify credit consumption semantics. An agent would need to consult sibling schemas or guess to invoke this tool correctly.

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?

With schema description coverage at only 21% (only audioWeight, styleWeight, and weirdnessConstraint are described), the description must compensate for 11 undocumented parameters. It only adds meaning for personaId ('supports personaId') and loosely maps 'uploaded source' to uploadUrl. The semantics of model, customMode, negativeTags, vocalGender, instrumental, and personaModel are left entirely unexplained, so agents will have to guess at their values.

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?

The description states a specific verb and resource ('cover generation from an uploaded source') that distinguishes it from siblings like suno_generate (text-to-music) and suno_extend (extending existing audio). The term 'cover' plus 'uploaded source' gives agents enough to select it over alternatives. It could be slightly more explicit about what 'cover' means, but it is not tautological or vague.

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?

No guidance on when to use this tool versus alternatives is provided. The description does not mention the prerequisite that uploadUrl must be obtained from suno_upload, nor does it route the agent to suno_poll/suno_tasks after receiving the task_id. The schema hints at the suno_upload dependency, but the description itself offers no usage context, leaving the agent to infer the workflow.

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