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

Annotations already declare readOnlyHint, idempotentHint, non-destructive and closed-world, and the description adds real value beyond them: the publisher, the 2025 granularity change, and the explicit no-substitution rule with a fallback that lists available years. It still says nothing about the shape of the response, such as how the single value versus the three usage-split values are returned.

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 purpose is front-loaded in the first clause, which is good. However, the entire content is then repeated verbatim in Chinese, doubling length without adding information for an agent that already parsed the English; one language would suffice unless bilingual indexing is a deliberate requirement.

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?

This is a simple read-only lookup with two fully described parameters and a complete safety profile in its annotations, and the description covers its data source and failure behavior. The only gap is that there is no output schema, so a short note on the returned fields would have made it fully self-contained.

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% and the schema already documents the 1990–2100 range, the usage_type enum meanings, and the default of returning all values when usage_type is omitted. The description's only addition is that pre-2025 years carry a single value, which largely restates the schema note, so the baseline of 3 is right.

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 a tightly scoped resource: the official Taiwan electricity emission factor in kgCO2e/kWh for a given year, with its publisher named. That resource scoping is enough to separate it from the generic siblings get_emission_factor and search_emission_factors without opening any schema.

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?

Explains when the usage_type distinction applies (only from the 2025 factor year) and what happens when data is unavailable: it reports the miss and returns the years that exist rather than substituting. It gives no explicit comparison to the sibling factor tools, so it stops short of full routing guidance.

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