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

Annotations already establish readOnly and non-destructive behavior, so the description adds critical behavioral context: refusal conditions (confidence 0.0, missing resolved_url), the 'no network call' property, and the strong prohibition against constructing inputs manually to prevent citation fabrication. No contradictions with annotations.

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?

Although somewhat long, every sentence delivers essential operational guidance: ordering, input provenance, refusal triggers, and anti-fabrication policy. The bold 'USE THIS TOOL AFTER' and 'DO NOT construct' warnings are prominent, and the text is well-structured for quick scanning.

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?

The description covers the full invocation context: pipeline position, input requirements, failure modes, and authoritative formatting behavior. With an output schema present, return-value details are unnecessary. The tool's high-stakes nature (citation fabrication) justifies the thorough guidance.

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 each parameter described as coming from citations_resolve, so the schema carries the parameter details. The description enhances this by mandating that fields must be passed directly from citations_resolve and never guessed, adding provenance semantics that reduce fabrication risk.

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 clearly states the tool's purpose: 'produce the correctly formatted OSCOLA citation string' and 'Formats per OSCOLA 4th edition rules for each citation type.' It also distinguishes itself from sibling tools by explicitly saying 'USE THIS TOOL AFTER citations_resolve,' positioning it as the formatting step in a two-tool pipeline.

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 gives explicit when-to-use guidance: 'USE THIS TOOL AFTER citations_resolve' and instructs to pass parsed fields directly. It also provides exclusions: refuses when confidence is 0.0 or when neutral citations lack a resolved_url, and tells the agent to surface the failure rather than fabricate a citation.

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