Suggest a proven prompt structure

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

The description supplements annotations by stating 'CAPABILITY: `read` — side-effect-free,' reinforcing the readOnly and non-destructive hints. It also details the ranking nuance: 'Organization winners rank above source-cited best-practice templates only when confidence is medium or high.' This adds behavioral context beyond the schema and 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 three sentences, front-loaded with the primary action, followed by usage guidance, ranking nuance, and a capability note. Every sentence contributes meaningful information without redundancy, and it is well-structured for quick parsing by an agent.

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 the core purpose, usage timing, mapping of kind values, and ranking behavior. It lacks details such as the number of results returned or pagination, but for a suggestion tool with read-only semantics and no output schema, it provides sufficient context for an agent to select and invoke it correctly. Sibling differentiation is implicitly handled via the 'before generating' directive.

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 67%, leaving the required 'kind' parameter without a description. The description compensates by explaining the semantic difference between POST_HOOK and VIDEO. Niche and platform already have schema descriptions, so the tool's description adds value primarily for the kind parameter, but not extensively for the others.

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 identifies the tool's function: 'Return ranked, evidence-labeled prompt scaffolds for the active organization.' It uses a specific verb (Return) and resource (prompt scaffolds), and the phrase 'Call this before generating any post or short' differentiates it from generation tools like create_drafts and shorts_generate.

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?

It explicitly states when to call the tool: 'before generating any post or short' and instructs to 'start from the first result.' It also maps the kind parameter to use cases: 'Use POST_HOOK for post openings and VIDEO for short-video structures.' This provides clear usage context, though it doesn't name specific alternative tools, the guidance is direct and actionable.

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