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

Annotations already declare readOnly/idempotent/non-destructive, so the safety profile is free; the description instead spends its budget on provenance and epistemic limits — factual statements grade A (official documents), the crosswalk itself grade B (Lab judgment, not an official mapping), and no mutual-recognition document as of 2026-10-26. That is exactly the caveat an agent needs before quoting output, though it does not describe result size or pagination.

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?

Front-loaded with a labeled Purpose/Guidelines/Modes/Limits/Ex structure so an agent can scan to the needed section, and every labeled block carries decision-relevant content. It is on the long side and the trailing examples partially restate the mode descriptions, which keeps it from a 5.

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 five-param lookup tool with an output schema and full annotation coverage, the description supplies everything an agent lacks structurally: mode semantics, provenance grading, the explicit date-stamped absence of an official mutual-recognition document, and companion tools. Return-value details are correctly left to the output schema.

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%, so the baseline is 3; the description earns more by adding a constraint the schema does not enforce — 'mode=lookup (default, needs product=)' despite an empty required array — plus worked examples showing a Chinese product term and response_format='json'. The keyword alias and language parameter are left to the schema, which is acceptable.

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 ('China-EU carbon footprint crosswalk', per-product comparison of CN certification vs EU CBAM/CSRD/ESPR requirements) and enumerates the exact outputs (overlap, shareable data, open gaps). It also names the adjacent tools (get_carbon_standards, query_cbam_emission_factors) and clarifies it is the crosswalk layer, not the underlying standards, so it is distinguishable from siblings.

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?

Gives explicit trigger conditions: 'call this whenever a question involves exporting to the EU, dual compliance, does China's certification get recognized by the EU, or comparing Chinese vs EU carbon requirements.' It also routes to alternatives for underlying data and says which mode to pick for which question, which is genuine when-to-use guidance.

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