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

No annotations are supplied, so the description carries the disclosure burden. It implies a read-only lookup and enumerates the returned fields, but never states read-only status, permission requirements, or whether the provenance is static or can change over time. For a zero-argument metadata tool the risk is low, so a minimal-but-adequate 3 is appropriate.

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?

Two sentences, front-loaded with the return contents before the usage hint. Efficient, though the second sentence slightly restates the first's implication that this is read for attribution purposes.

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 no output schema, so the description usefully enumerates the returned fields (source, date computed, licence, citation), which is the main completeness gap it must fill. Small details such as licence format or citation style remain unspecified but are not essential to calling the tool correctly.

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 tool takes no parameters and the schema is an empty object, so there is nothing for the description to clarify or compensate for. Baseline 4 applies.

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 names a specific resource (the Bags That Pay dataset) and enumerates what it returns: source, computation date, licence and citation. It is clearly distinguishable in spirit from data-reading siblings such as dataset_columns or dataset_stats, though it never names an alternative to sharpen the boundary.

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?

"Read this to attribute a figure correctly" gives a concrete trigger condition for when to reach for this tool rather than a data-access sibling. It stops short of stating exclusions or explicitly naming the alternative tools for non-attribution needs.

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