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

Annotations already declare the safe read-only/idempotent profile, and the description still adds substantive behavior: Markdown layout, per-paragraph translation provenance (MoJ translation, slip-corrected, or machine), per-line address and URLs, citation graph, and sources. It also discloses the negative behaviors that matter most — a law returns only an overview, and a date with no held text is refused rather than answered with the nearest text.

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 the core action and the provision-vs-law split before the finer detail, and nearly every clause carries information. The sentences are long and clause-stacked, which costs some readability, but there is little dead weight.

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 4-parameter read tool with full schema coverage, annotations, and an output schema, the description supplies everything an agent needs: both id forms, what each returns, translation provenance, version selection, and the refusal case. No material gap remains.

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 real meaning beyond the schema: why asOf/version exist (an earlier text, or one an amendment not yet in force will leave) and that a japanlaw.org URL is accepted as an id. It stops short of the mutual-exclusion and format details, which the schema already carries.

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 and resource ('Read in full a law or provision ... by its id') and splits the two id shapes into distinct outcomes, so an agent knows exactly what comes back. It never names the overlapping siblings get_provision and get_law, so the boundary with those tools is only implied (via 'in full' and the lang note about get_provision's card).

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?

Clear context: use it on an id 'search found', with explicit routing between a provision id (full text) and a law id (overview, 'never its whole text'), and the asOf/version fork for reading a non-current text. No explicit when-not or sibling routing against get_law/get_provision, which is the main remaining gap.

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