Episode-over-episode race, normalised by age

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

Beyond the readOnlyHint and idempotentHint annotations, the description discloses quota costs ('Costs 1 YouTube Data API quota unit for publish dates... plus one Analytics query per video') and the exact output structure ('cumulative curve... leaderboard... raw per-day API values'). This is rich behavioral context not present in 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?

Four sentences, each serving a distinct purpose: purpose, motivation, output, and cost. No filler or repetition of schema fields.

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 read-only comparison tool, the description covers the core value proposition, the output content, and resource costs. Without an output schema, the return description suffices to set expectations. The missing elements (e.g., exact leaderboard computation) are minor.

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 input schema already provides 100% description coverage for all four parameters, including detailed semantics for window_days and metric. The tool description adds conceptual framing (normalization by age) but not additional per-parameter syntax, so it neither supplements nor conflicts with the schema.

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 'The derived view: compare several videos on equal terms' immediately stating the tool's function. It specifies the mechanism (re-indexing to days since publish) and distinguishes from raw totals, making it clearly distinct from sibling performance tools.

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 explicitly frames the use case with 'Raw totals cannot answer "is this episode outperforming?" because an older video has simply had more days to accumulate; this removes that.' This tells the agent when to use the tool (fair episode comparison) and when not (raw totals), though it does not name a specific sibling tool as an alternative.

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