sapiens_musicator

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

Beyond the sparse annotations (readOnlyHint=false, openWorldHint=true), the description discloses per-action costs, render's fire-and-forget async behavior, publish's side effects echoing to Chat and Fórum, owner scoping, and the rendering status lifecycle. This is rich behavioral context with no contradiction against the annotations.

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?

The description is dense but organized: overview, sub-action list with costs and effects, then the recommended flow and ownership scope. The length is justified by seven sub-actions and several operational details, though the opening sentence mixes cost data into the overview, making it slightly less scannable than it could be with a more structured layout.

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 complexity of 13 parameters, seven sub-actions, and no output schema, the description covers the full lifecycle, permissions, costs, side effects, and enough return hints (trackId, list fields, get fields) for an agent to call and sequence the tool correctly. Nothing essential for selection or invocation 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 92%, so the baseline is already 3. The description adds action-level semantic meaning: trackId is required for render/get but optional and persistence-oriented for lyrics, create returns a trackId at zero cost, and list returns track metadata including status and audio. This goes beyond the schema's per-parameter descriptions without repeating all thirteen parameters.

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 opening sentence names the tool as a complete music loop via Sapiens voice without requiring the UI, and immediately enumerates seven concrete sub-actions (create, lyrics, list, get, render, publish, list_public). This is a specific verb+resource framing that clearly differentiates it from the broader sapiens_* siblings like stock audio, studios, or video tools.

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?

The description provides an explicit full workflow: create → lyrics(trackId) → render → get → publish, and gives per-action conditions such as render being asynchronous fire-and-forget, publish being curated and idempotent, and list_public requiring no login. It lacks an explicit 'when not to use' sibling comparison, but inside this multi-action tool the routing guidance is strong.

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