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

With readOnlyHint and idempotentHint already declared, the description adds meaningful behavior: it discloses that large results 'spill to DataCanvas for SQL querying' and that truncated: true may appear, and it clarifies temporal window semantics (past_days before today, forecast_days ahead). It slightly overlaps with the schema's past_days note about ERA5 lag, but this is complementary reinforcement rather than redundancy. No contradiction with 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 highly information-dense)Skip; every paragraph adds unique value: tool differentiation, variable categories, output format, spillover behavior. It is front-loaded with the core purpose ('hourly and/or daily variables for coordinates') and avoids fluff, though the variable lists could be trimmed since they echo the schema examples.

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 an 11-parameter tool, the description covers all decision-relevant context: temporal window (past_days + forecast_days), variable categorization rules with concrete examples, unit options, response structure per entry, spillover behavior for large queries, and the requirement for at least one variable array. The schema itself is rich, but the description adds the 'when to use' guidance and boundary conditions (e.g., hourly names rejected in daily_variables) that the schema alone cannot convey.

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%, but the description adds significant value: it lists common variables per category (e.g., weather_code, wind_gusts_10m for hourly; temperature_2m_max for daily), explains why an hourly variable like cloud_cover must use the 'published aggregate' (cloud_cover_max) for daily requests, and clarifies the past_days vs. historical tool tradeoff. This goes beyond the schema's terse field docs.

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 ('Get Forecast') and immediately elaborates: 'hourly and/or daily variables for up to 16 days ahead, with optional past_days (up to 92) for recent history.' It clearly differentiates from the sibling openmeteo_get_historical by explicitly saying when to prefer this tool for recent data. The output format is described in detail (per-entry 'time' field and one key per variable), making the tool's purpose unmistakable.

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 explicitly tells the agent when to use this tool over openmeteo_get_historical ('Use past_days... since ERA5 has a variable lag'), explains the hourly vs. daily variable split with rejections, and notes DataCanvas spillover for large queries. It also states the requirement that at least one of hourly_variables or daily_variables must be provided, giving clear invocation guidance.

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