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

Annotations already declare readOnly, idempotent, openWorld and non-destructive, so the description is not required to establish safety. It still adds real behavioral context beyond them: the text comes from the official consolidated version, reflects the version in force today or on any asOf date, and includes in-force status and amendment provenance. It also discloses a per-call price ($0.005 per act-lookup), which matters for an agent budgeting calls; only failure modes for unknown or ambiguous articles are left unstated.

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 opening clause is well front-loaded with two concrete example questions that immediately anchor the tool. The second sentence ("Built for AI agents doing legal and compliance work, and for people who want a sourced answer without XML") is promotional and largely redundant, though the pricing line that follows carries genuine decision value. Tightening would remove roughly a quarter of the text with no loss.

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 six parameters, no output schema, and only one required field, the definition covers the essentials: what is returned (article text), in what state (in force on a date, with amendment history), and at what cost. Because no output schema exists, the description's sketch of the response contents is genuinely load-bearing. Missing only edge-case behavior, such as what happens when an article reference is ambiguous or not found.

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 100% and each of the six parameters already carries examples and patterns, so the schema does the heavy lifting. The description reinforces the asOf point-in-time semantics ("today (or on any date)") but adds no syntax, default, or constraint information beyond the schema. A baseline 3 is appropriate.

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 concrete verb and resource: return the section or article text from the official consolidated version in force on a given date, plus in-force status and amendment history. The worked examples ("section 172 of the Companies Act 2006", "artikel 7:658 BW") make the UK/NL statute scope unmistakable. It does not name the near siblings (eu_law_lookup, dutch_case_law), so the agent must infer the boundary itself.

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?

Usage is conveyed only through example questions about statutes, which implies this is the tool for citing legislation text. There is no explicit when-to-use versus eu_law_lookup (EU instruments) or dutch_case_law (case law), and no stated exclusions or prerequisites. An agent can guess the routing, but the definition does not do the routing for it.

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