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

Annotations already cover safety (readOnly, idempotent, non-destructive, closed-world), so this is not the description's burden. The description nonetheless adds genuine behavioral context: the result splits activity-data effect from factor effect, and it flags method mismatches so a difference is not misread as a reduction. That is real value about how to interpret output.

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 English text is two tight, front-loaded sentences that each earn their place, and the key caveat about method differences is placed last as a warning. The full bilingual duplication roughly doubles length for the same content, which is a minor structural cost.

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 tool has complex nested inputs but no output schema, so the description must convey what comes back. It does explain the conceptual return (separated activity vs. factor effects, method-mismatch flag), which is enough to call and interpret it; exact result field shapes remain unspecified.

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?

With 100% schema description coverage and deeply annotated nested objects (factor_id, quantity_unit, year, optional_context, refrigerant, lower_heating_value), the schema carries parameter meaning almost entirely. The description only conveys that two calculation objects are supplied (baseline and comparison), so the baseline score of 3 is appropriate.

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 states a specific verb and resource ('Compare two calculations') and adds scope via the effect-decomposition it performs, which helps separate it from calculate_emissions. It stops short of naming a sibling or explicitly stating what it does not do, so it is clear but not fully differentiated.

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 parenthetical '(for example two years)' implies the comparison use case, and the mention of differing calculation methods hints at a caveat to check. There is no explicit when-to-use vs. when-not guidance and no named alternative such as calculate_emissions for single-period results.

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