get_legislation_provision

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

With no annotations, the description carries the disclosure burden and does real work: it warns that some jurisdictions return only as-enacted text and tells the agent to check the 'Text as of' field and any warning at the top of the result. That is a genuine behavioral trait an agent would otherwise misread. It says nothing about permissions, failure modes for a missing provision, or handling of very long provisions.

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 single-sentence purpose, then the caveat, then argument formats — a sensible order. The args block is long but every example earns its place by disambiguating accepted citation formats; only the multi-line wrapping of the gb provision examples feels slightly sprawling.

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?

An output schema exists, so return values need not be described, and the description still flags the one result-level field worth checking ('Text as of' plus warnings). Combined with fully documented parameters, the definition is sufficient to call the tool correctly; minor gaps remain around what happens when a provision id does not resolve.

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 0%, so the description must compensate, and it does: each of the three required parameters is explained with provenance (code from list_jurisdictions, law id from search_legislation) and per-jurisdiction example formats. The provision examples ('s.172', 'section/172', 'sch 1 para 2', 'schedule/1/paragraph/2') convey accepted syntax that the schema does not.

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 first line states the resource precisely — a single article/section/regulation/schedule paragraph — which is clearly narrower than the sibling get_legislation_text. It is a noun phrase rather than a verb+resource construction, but an agent can still immediately tell what is returned and how it differs from whole-law retrieval.

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?

It gives concrete prerequisite workflow by naming where each argument comes from: jurisdiction from list_jurisdictions, id from search_legislation. What's missing is an explicit statement of when NOT to call it (e.g. use get_legislation_text for the whole act), so the alternative-selection guidance is implied rather than stated.

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