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

No annotations are provided, so the description carries the full burden. It communicates that this is a read-only lookup ('Read this') and enumerates exactly what information will be returned: source, computed date, licence, and citation. Some output formatting details are omitted, but there are no hidden effects or destructive behaviors to disclose.

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 sentence plus title conveys the resource, the specific metadata fields, and the intended use. Every part contributes; there is no repetition or filler.

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?

For a zero-parameter read-only provenance tool with no output schema, the description is sufficient: it names the dataset, lists the returned metadata dimensions, and states the intended use case. No additional structured fields need clarification.

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 has zero parametersags, so the baseline is 4; the description does not need to add parameter meaning. It instead clarifies what the tool returns, which is appropriate for a no-input provenance endpoint.

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 states a specific verb ('Read'), a clear resource (dataset provenance), and the exact content returned: source, computed date, licence, and citation. The title reinforces this by framing it as where data comes from and how to cite it, making the tool's role unambiguous relative to sibling dataset tools.

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 explicitly tells the agent when to use the tool: 'Read this to attribute a figure correctly.' It does not enumerate exclusions or contrast with sibling tools, but the intended use case is clear enough for a zero-parameter provenance lookup.

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