get_dataset_schema

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

No annotations are provided, so the description carries the full burden of behavioral disclosure. It does an excellent job explaining the semantics of tricky fields like source_health (inaccessible vs unknown), source_health_detail (fixed reason code), and freshness (overdue meaning). It also discloses that raw provider URLs and credentials are excluded, which is important for agent expectations. It mentions the read-only nature implicitly by describing data retrieval, but does not explicitly state 'this is a read-only operation'. Given the lack of annotations, this is a strong effort, but could be a 5 if it explicitly stated it does not modify data.

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 thorough and well-structured. It starts with a clear summary sentence, then details the return fields and their semantics, and ends with usage guidance. It is moderately long but every sentence adds critical information about field meanings and exclusions. The main body is front-loaded with the tool's purpose. It could be slightly trimmed, but the richness justifies the length. A 5 would require even more efficiency, but this is clean.

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 single parameter, no output schema, and no annotations, the description provides comprehensive information: what is returned (columns, geometry, etc.), the meaning of all status fields, and exclusions. It also gives usage context ('before writing spatial questions'), which is crucial for correct invocation. The agent has everything needed to call the tool correctly and interpret results. This is complete for its complexity.

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?

The schema has 0% description coverage for the single parameter, dataset_id. The tool description provides context: 'Dataset id (e.g. from search_datasets).' This is minimal but adds value by indicating the source of the ID. However, it doesn't describe format or constraints, but the parameter is simple. Given the low schema coverage, the description partially compensates, but could be improved by explicitly saying 'A string identifier of the dataset as returned by search_datasets'.

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 explicitly states the tool's purpose: retrieving a dataset's schema and source trust metadata. It enumerates the specific elements returned (columns, geometry, CRS, etc.), distinguishing it clearly from siblings like search_datasets (which finds datasets) and get_features (which retrieves data). The verb 'get' is precise and the resource is identifiable.

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 provides clear usage guidance: 'Call this before writing spatial questions so you know both the available columns and whether the source may be stale.' This tells the agent when to use it in a workflow. It does not explicitly mention when not to use it or name alternatives, but the context is strong enough to differentiate from search_datasets and get_features. It could be improved by explicitly stating 'use search_datasets to find datasets' but that's implied.

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