What to make next

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

Annotations already declare readOnlyHint and openWorldHint, and the description still adds real behavioral context: the tool has two distinct modes depending on whether an AI model is configured, returning either structured ideas (angle, why now, thumbnail concept, confidence) or raw data. That dual-mode disclosure is exactly the kind of context annotations cannot convey.

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?

A single dense sentence that front-loads the core value (next video ideas from channel data), then brackets the evidence sources, then the two output modes. No filler and nothing buried.

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?

With no output schema, the description usefully explains what ideas contain, which covers the return shape. But for a 4-parameter tool at 50% schema coverage, the missing explanation of count and template leaves an agent guessing about volume control and template selection.

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 coverage is 50%, so half the parameters are documented only in the schema. The description illuminates focus ('a topic to research') and indirectly channel ('this channel's data'), but says nothing about count (default 10, range 3-20) or the entirely undocumented template parameter.

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?

States a specific verb and resource — generating next video ideas grounded in this channel's own performance data — and names the concrete inputs (outliers, underperformers, optional research topic). It is clearly distinguishable from siblings like find_outliers or research_topic, though it never names them explicitly.

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?

Use is implied by 'next video ideas grounded in this channel's data' and the optional topic parameter, so an agent can infer the scenario. However, there is no explicit when-not guidance and no pointer to alternatives (find_outliers, research_topic, suggest_shorts) that an agent might otherwise pick.

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