sapiens_shorts

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

With only readOnlyHint=false and openWorldHint=true in the annotations, the description carries the full burden and does so thoroughly. It discloses that render is asynchronous, what the immediate return shape is ({imageId, status:'rendering', url:null}), that the resulting VEO URL expires quickly, that the operation is admin-only, and that imageId must reference an existing generatedImages row with cost defined. No annotation contradiction.

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?

Every sentence earns its place: purpose first, then argument map, then async behavior, then prerequisites and fallback creation path. Though dense, there is no fluff or repetition, and the most decision-critical details (async, polling, expiration) are prominently marked.

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?

For a complex async tool with no output schema, the description is remarkably complete. It provides the return shape, the polling workflow until completed/error, the URL expiration warning, the admin-only restriction, prerequisites, and how to satisfy them through sibling tools. An agent has everything needed to invoke and monitor the operation 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?

Schema description coverage is only 40%, but the description compensates comprehensively. It explains imageId as a pre-existing persona found via sapiens_gallery, lists styleId options inline, summarizes the brief structure as product+hook+shots+vibe, and clarifies that references are optional base64 start/end frames defaulting to the persona as start frame.

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 opens with a precise verb and resource: 'render vertical 9:16 via VEO com brief estruturado (admin-only)'. It also names the sub-action 'render' and enumerates the exact inputs, making it clearly distinct from siblings like sapiens_video (status polling) and sapiens_image (image generation).

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 gives explicit workflow guidance: use sapiens_gallery to discover imageId, call sapiens_video action=status to poll, and use sapiens_image action=request_generation to create a prerequisite row when it does not exist. This tells the agent not only when to use this tool but which sibling handles the adjacent steps.

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