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

Annotations already mark readOnlyHint=true, and the description reinforces this by describing a read-only score return. It adds behavioral context beyond annotations: 'Updates: monthly' and the output components (trend, confidence, ranked top_drivers, methodology_version, freshness), which inform the agent of data freshness and response shape. This is useful and non-contradictory.

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 and front-loaded: the first sentence defines the output, the second gives usage triggers, and the third states update frequency. Every sentence earns its place with no filler or redundant restatement.

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?

Given the tool's low complexity (one optional parameter, no output schema), the description is complete: it lists output fields, specifies when to use the tool, and notes the monthly update cadence. The schema covers the days parameter and Gold tier nuance, so the description does not need to repeat that.

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 100% for the single optional 'days' parameter, which is already described in detail (history series, up to 5 years, Gold tier requirement). The description adds no extra parameter semantics, so the baseline of 3 applies.

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 a specific verb and resource: 'Returns a 0-100 AI energy-intensity score' and details the score's composition (PUE trends vs compute-throughput growth, energy-per-token direction). This clearly distinguishes it from sibling tools by naming a unique metric and its output components.

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 states when to call: 'Call when the user asks about AI energy costs, energy-per-token, GPU power efficiency, data-center PUE, or LLM marginal-cost inflection, or when timing GPU capacity commitments, colocation power contracts, or inference-pricing decisions.' It provides clear context but does not mention when not to use it or alternatives, so it stops short of a 5.

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