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

Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, covering the safety profile well. The description adds that it returns metadata (schema, filters, limits, freshness, access details) but doesn't disclose rate limits, pagination, or error behavior. With strong annotations carrying the safety burden, the modest addition is acceptable.

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?

A single clear sentence that front-loads the primary function and enumerates the return fields. There is zero waste, and every word earns its place. Efficient and readable.

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?

There is an output schema provided, so the need to document return values is reduced. The tool has only one parameter fully covered by the schema, and annotations fully cover the safety profile. The description is complete for a simple metadata-lookup tool given the richness of structured fields available.

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%, with the dataset_id parameter fully documented in the schema (pattern, constraints, and origin: "from datasets_list or datasets_search"). The description adds the notion that this is the identifier being described, which is largely handled by context. With baseline 3 at 100% coverage, the description's clarity about what the parameter refers to bumps it slightly.

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 uses a clear verb ("Return") with a specific resource (schema, filters, limits, freshness, and access details) for one dataset identifier. It's clear what the tool does, though it doesn't explicitly differentiate from sibling tools like catalog_describe or datasets_list, which could be confused with it. The title and name are also clear.

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 states the single input (dataset identifier) and the return content (schema, filters, limits, freshness, access details). It implies this tool is the metadata-lookup counterpart to datasets_list and datasets_search, but it doesn't explicitly state when to use it vs those siblings or provide exclusions. Usage context is implied rather than stated.

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