create_central_visual_prompt

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

Beyond the readOnlyHint annotation, the description adds behavioral context by explaining the expected workflow: the assistant must generate, inspect, and save the image, then pass heroImage to create_one_pager. It also reiterates non-generation, which aligns with the read-only nature. This provides more insight than the annotation alone.

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 concise—two sentences—and front-loads the primary purpose. It efficiently conveys the core function and essential workflow without extraneous information. Every sentence contributes value.

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 tool has a complex input schema, but the description lacks details about output (what is returned) and the specific structure of the 'content' object. It gives a high-level purpose and hints at the workflow but omits critical information like return format or parameter semantics. This leaves gaps for an agent to discover on its own.

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?

The schema has a single 'content' parameter with a complex nested structure (dozens of fields, some required). The description only refers to it as 'full one-pager content' without explaining the fields, their constraints, or how to populate them. Since schema coverage is 0%, the description fails to compensate, leaving the agent to infer the structure from the schema alone.

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 function: 'Prepare a topic-specific image-generation prompt from the full one-pager content.' It also explicitly clarifies that it does not generate the image itself, distinguishing it from image-generation tools. This is specific and unambiguous.

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 workflow guidance: 'The calling assistant must generate and inspect the image using its connected image tool, save it in inputs, and pass heroImage to create_one_pager.' This indicates when to use the tool (before creating the one-pager) and the necessary follow-up steps. However, it does not explicitly compare with sibling tools like create_generation_prompt, so it's not fully exhaustive.

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