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

The description richly discloses behavior beyond annotations: it performs a live TNA HEAD check, sets confidence to 0.0 on non-200, raises ToolError with a transient error category and retryable flag, and attempts one retry. These details are not present in the annotations and are critical for agent decision-making.

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?

The description is front-loaded with a bold imperative, followed by concise actionable sections covering resolution behavior, error handling, and anti-fabrication guidance. Every sentence adds value; there is no repetition of schema/annotation content 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 network-dependent resolution tool, the description covers the full context: live verification, failure semantics, retry behavior, and the safe fallback when resolution fails. The presence of an output schema means return-value details need not be spelled out, and the description still provides enough for an agent to select and invoke 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 input schema already provides 100% coverage for the single parameter with examples. The description adds further semantic context by enumerating citation types ('neutral citation, SI, legislation section, retained EU law') beyond the schema examples, and explains the resolution behavior tied to the parameter, adding value over the schema baseline.

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+resource: 'Parses + resolves a single citation ... and returns parsed fields plus resolved_url.' It clearly distinguishes itself from siblings by instructing to use this tool BEFORE constructing an OSCOLA citation string from known fields, separating it from formatting and parsing 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 states when to use the tool ('USE THIS TOOL BEFORE constructing an OSCOLA citation string from known fields, OR to confirm a citation points at a real document') and when not to ('Do NOT format or quote a confidence-0.0 citation'). It warns against fabrication but does not explicitly name alternative sibling tools, so it falls just short of a 5.

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