Atmospheric CO2 (Keeling Curve)

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

Annotations already declare readOnly, idempotent, and open world. Description adds source, units (ppm), monthly frequency, and default range—useful context beyond 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?

Three clear, front-loaded sentences with zero filler. Every sentence adds value: data source, format, default behavior.

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?

Covers essential info: what, source, time range, default. Output schema exists so return format is not needed. Minor gap: could clarify that 'years' goes backward from current date.

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?

Only parameter 'years' is fully documented in schema (100% coverage). Description repeats default but adds no new semantic meaning beyond 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?

Clearly states it returns atmospheric CO2 from NOAA Mauna Loa (Keeling Curve), monthly ppm since 1958. Specific verb 'returns', distinct resource, and differentiates from sibling climate indicators.

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?

Provides default behavior (10 years) but no guidance on when to use this vs other climate indicators like methane or temperature. Implied usage for CO2 data, but no explicit alternatives.

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