get_article

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

While annotations declare the operation read-only/safe, the description adds critical behavioral context: variable token costs (500-70,000), automatic truncation thresholds (50,000 characters), and notification behavior when truncation occurs—essential for agent resource management.

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?

Three sentences total, each earning its place: purpose declaration, cost/limit warning, and workflow prerequisite. No redundancy or filler; information density is high with critical constraints front-loaded.

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 complexity of retrieving large legal texts, the description adequately covers cost risks, size limits, and prerequisites. Minor gap: does not explicitly describe the output format/structure (e.g., markdown vs JSON), though truncation behavior implies text content.

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?

With 100% schema description coverage, the parameters (regulation ID, article number, include_recitals) are fully documented in the schema. The description aligns with these ('specific article from a regulation') but does not add syntax details beyond the schema, warranting the baseline score.

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 ('Retrieve') and clear resource ('full text of a specific article from a regulation'), immediately distinguishing it from siblings like search_regulations or get_recital.

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?

Explicitly prescribes a workflow ('Use search_regulations first to find relevant articles'), providing clear guidance on when to use this tool versus its search counterpart, and warns about token costs that would influence invocation decisions.

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