Why a given month behaves the way it does on one of the four rivers: the seasonal hydrology, the thirty-year frequency, and the last five years' outcomes for that month.
| Name | Required | Description | Default |
|---|---|---|---|
| month | Yes | ||
| river | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the full transparency burden. It discloses the categories of data returned (hydrology, 30-year frequency, last five years' outcomes), which is helpful, but it does not mention whether the operation is read-only, any side effects, limitations, or data freshness.
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 a single, well-structured sentence that front-loads the purpose and itemizes the three output facets. There is no redundancy or filler, making it highly concise and easy to parse.
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 simple 2-enum-parameter tool with no output schema and no annotations, the description adequately covers the main output types and enough context for an agent to invoke it correctly. It falls short only in not specifying output format or edge conditions, but the tool is straightforward enough that this is not a critical gap.
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 0%, so the description is the only source of parameter meaning. It does tie the parameters to the tool's purpose ('one of the four rivers', 'a given month'), but it adds no detail about how specific values affect the response. The enums in the schema already list valid values, so the description adds minimal semantic value beyond that.
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 explains what the tool provides: an analysis of why a given month behaves as it does on one of four rivers, including seasonal hydrology, 30-year frequency, and recent outcomes. It distinguishes itself from siblings like get_live_gauges and get_monthly_odds by focusing on explanatory detail rather than live readings or probabilities.
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 implies use when one needs explanatory context for a month on a river, but it does not explicitly state when to prefer this over sibling tools or mention any exclusions. The purpose is clear enough to infer usage, but no alternative guidance is provided.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.
Each tool targets a distinct need: live readings, month explanations, 12-month odds, and specific cruise scoring. No two tools overlap in purpose.
Three tools follow get_ convention, but score_sailing uses a different verb. Minor deviation does not affect clarity.
Four tools cover the domain without redundancy or bloat. Each serves a clear role in assessing river cruise risk.
The set covers current conditions, month-level explanation, forward-looking odds, and cruise-specific scoring. Minor gaps like historical raw data or river metadata exist but don't undermine core workflows.
