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

Annotations already declare readOnlyHint=true and openWorldHint=true, but the description adds substantial non-obvious behavioral details: the per-request date range limits (1 year vs 10 years), the special proxy year for normals, and the crucial units behavior (raw tenths-of-unit integers unless units=metric/standard is passed). It also states the return format (flat tuples). This goes well beyond the annotations and provides the agent with critical knowledge to correctly interpret results.

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 (six sentences) but every sentence carries critical information: purpose, required params, date limits, normals exception, return format, and units warning. It is front-loaded with the core purpose and requirements. While concise would be shorter, the density of essential pitfalls justifies the length. Slightly verbose but not wasteful.

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 12 parameters, 3 required, an output schema, and annotations, the description covers the main decision points: what to pass, how to bound the date range, how to handle normals, and how to read values. It does not explicitly mention pagination strategy (offset/limit) or how to discover station IDs, but those are covered in the schema (e.g., stationId description says to use noaa_climate_find_stations). The output schema provides return structure, so the description need not repeat that. Overall, nothing critical is missing for a competent agent.

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 description coverage is 100%, but the description adds meaning beyond the schema: it gives concrete dataset examples (GHCND, GSOM), explicitly ties date limits to dataset groups, warns about the units pitfall ('TMAX=256 = 25.6°C'), and explains the proxy-year behavior for normals. These details are not in the schema and meaningfully increase the agent's ability to call the tool correctly.

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 opens with a specific verb and resource: 'Fetch historical observation records from a NOAA CDO dataset for a given date range.' It clearly separates this from the sibling metadata/list tools (find_stations, list_datasets, etc.) by focusing on data retrieval. The verb 'fetch' plus the resource 'historical observation records' is unambiguous.

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 context on what the tool needs (datasetId, startDate, endDate) and provides detailed guidance on date range limits per dataset type, plus a special instruction for NORMAL_* datasets to use the 2010 proxy year. It does not explicitly contrast this tool with alternatives (e.g., 'use this tool when... not when...'), but the sibling tools are all lookup/metadata operations, so the usage context is clear by implication. No explicit exclusions are given, hence a 4.

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