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

Annotations declare readOnlyHint=true and destructiveHint=false, so the description adds value by detailing caching (7-day), SLA (≤20s), data sources (Open-Meteo CMIP6, IPCC AR6 Atlas, NOAA SLR), and output nature (multi-scenario comparison, probabilities, business impact signals). This contextualizes behavior beyond the 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?

The description is long but well-structured, front-loading the core purpose then logically presenting scenarios, horizons, metrics, outputs, sources, and use cases. Every sentence adds value, though it could be slightly more concise by removing repetitive elements like 'SLA ≤20s' integration into the caching statement.

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 complexity (6 parameters, nested location object, multiple scenario families and metrics), the description covers purpose, scenarios, metrics, outputs, use cases, caching, SLA, and sources. Since an output schema exists, the description does not need to detail return values, yet it still describes output types (multi-scenario comparison, probabilities, business impact signals) for context.

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?

Input schema covers all 6 parameters with descriptions (100% coverage). The description adds meaning by elaborating on metrics (e.g., 'temperature (delta vs baseline 1990-2010, days >35°C, hot nights)') and explaining the 'all' scenario option. This extra context helps agents understand the parameter options beyond the schema's enum labels.

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 clearly states the tool provides long-term climate projections by IPCC scenario for any location. It lists specific scenarios (RCP_4_5, RCP_8_5, SSP1_2_6, etc.), metrics (temperature, precipitation, sea level, etc.), and output types (multi-scenario comparison, IPCC probability, business impact signals). This specificity distinguishes it from siblings like weather_climate_intel, which likely covers short-term weather.

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 lists explicit use cases such as TCFD/CSRD physical risk, long-term asset due diligence, catastrophe insurance, and infrastructure planning. It does not explicitly state when to avoid this tool or mention alternative tools, but the use-case list provides clear context for selection.

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