jma_get_forecast

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

With no annotations, the description carries the full burden and does so well: it discloses issuance cadence (≈05:00, 11:00, 17:00 JST), timezone handling (+09:00), the Japanese-verbatim vs. weather_en label distinction, and what the response contains. It omits error behavior for invalid areas and any rate/availability limits, keeping it from a 5.

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 purpose, then a structured 'Returns:' enumeration and operational notes. The returns sentence is long, but every clause (wave height, reliability grades, normals, forecaster overview) is load-bearing because no output schema exists.

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?

No output schema exists, so the description must explain the return payload — and it does exhaustively: per-block precipitation, temperatures, 7-day outlook with reliability grades and climate normals, plus the written overview. Combined with timezone and issuance notes, an agent has everything needed to call and interpret results.

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 already 100% and documents accepted scripts and area codes, so the baseline is 3. The description adds genuine semantics beyond the schema by explaining that naming a municipality narrows results to its sub-region, clarifying how granularity is chosen through the single `area` parameter.

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 — a JMA weather forecast for a place in Japan — and its scope (per prefecture-level office, today + 2 days + 7-day outlook) is unmistakable. It is clearly distinct from siblings like jma_get_warnings or jma_list_earthquakes, so an agent can select it without opening another schema.

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 gives clear usage context: name a municipality to narrow to its sub-region, or supply a JMA area code 'from jma_find_area', which implicitly routes the agent to that sibling for lookup. It does not state explicit exclusions (e.g., forecasts vs. warnings), so it stops short of a 5.

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