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

Beyond the readOnly/openWorld/idempotent annotations, it discloses the licensing constraint (Open Justice Licence forbids bulk/computational extraction, per-query pass-through, one judgment at a time), the ~2001-onward coverage window, and that a 0-row result means 'not found here' rather than 'does not exist'. These are non-obvious operational facts an agent could not infer from the schema or 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?

Front-loaded with purpose and scope, then a clear NOT-block and a disambiguation line. Dense and long, but nearly every clause carries routing or coverage information; the final US-corpus sentence is slightly verbose though it earns its place as an anti-hallucination guard.

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?

No output schema exists, yet the description enumerates the returned fields (case name, neutral citation with example format, court, judgment date, link, plus the fetch identifier). Combined with the coverage caveats and licensing limits, an agent has everything needed to call this correctly and interpret empty results.

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%, so the baseline is 3, but the description adds value by framing the searchable dimensions ('by subject, party name or judge') and by explaining that the returned identifier is the key get_uk_judgment reads — linking this tool's output to a sibling's input. It stops short of adding format or matching-behavior detail for individual params.

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?

Opens with a specific verb+resource ('Search UK court judgments and tribunal decisions') and enumerates the covered courts and source (National Archives' Find Case Law). It also distinguishes itself from search_case_law/find_case by declaring the US corpus out of scope, so an agent can separate it from siblings without opening a schema.

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 states when to use it ('England & Wales and UK-wide law') and when not to, with a detailed NOT-list covering Crown/County/Magistrates' courts, Scotland/NI, first-tier Employment Tribunal, dockets, and citator signals. It names the alternative tools for US law and warns that a US authority is a wrong answer, giving the agent a hard routing rule.

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