shot_prompt_render

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

The description explains the core transformation (expand into prompts) but omits side effects, error handling, or performance characteristics. With no annotations, the agent lacks insight into whether this is read-only, idempotent, or what occurs with invalid inputs.

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 a single concise sentence for purpose followed by a bulleted argument list. It is front-loaded, scannable, and contains no superfluous text.

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?

The description covers purpose and parameters adequately. However, it lacks workflow integration hints (e.g., using storyboard_read prior) and does not address prerequisites or failure modes. Given the output schema exists, return values are acceptable, but completeness for a tool with 2 required params could include more context.

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?

Despite zero schema description coverage, the description adds critical meaning: project_path must be absolute and contain specific files, shot can be an id or row number. This fully compensates for the schema's lack of descriptions.

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 clearly states the tool's action ('Expand one storyboard shot') and resource ('storyboard shot'), yielding specific outputs ('prompt and negative_prompt strings'). It is distinct from sibling tools like storyboard_read, which reads the entire storyboard, and style_pack_read, which reads style files.

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 explicit instructions for each parameter, including required file contents (style.md and storyboard.md) and shot identification format. However, it does not explicitly state when to use this over alternatives or exclude cases (e.g., after reading storyboard with storyboard_read).

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