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

Goes well past the readOnlyHint/openWorldHint annotations: it discloses the exact return payload and its equivalence to GET /authorities/{id}/viewer, the scroll-and-highlight side effect of paragraph_ref, and the non-obvious trap that an undeclared argument is silently dropped by FastMCP, causing every page turn to refetch page 1. That last detail is exactly the kind of behavior an agent cannot learn from structured fields.

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 return shape, then a conditional behavior sentence, then parameter docs. The Args block is slightly verbose and the FastMCP implementation note is long, but every sentence carries actionable information.

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?

With no output schema, the description covers the return payload shape at a high level, and it fully accounts for all three parameters and the paging mechanism. It stops short of describing payload size or pagination limits, which matters for a viewer that pages through judgment paragraphs.

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 description coverage is 0%, so the description carries the whole burden and does so well: all three params get concrete examples ("uk.case.uksc.2019.38", "45" / "para 12") and paragraph_offset is explained as 0-based plus why it must be declared. Only the accepted range for paragraph_offset is left unspecified.

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?

States a specific verb+resource ("Open the interactive case viewer for an authority") and immediately names the payload it returns (judgment paragraphs, cites, cited-by, test elements), which distinguishes it from pure text readers. It does not, however, contrast itself with close siblings like read_judgment_text or get_authority_detail, so an agent must infer the difference.

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 mention that paragraph_ref comes "from search_extracts" implies a search-then-open workflow, and the paragraph_ref/offset behavior hints at page-turning usage. But there is no explicit statement of when to pick this over read_judgment_text or get_authority_paragraphs, and no exclusion conditions.

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