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

Annotations already declare readOnly, idempotent, openWorld and non-destructive, so the safety profile is covered. The description adds two pieces of real behavioral context beyond that: the answer is drawn from the consolidated version in force (or as of a given date), and the call costs $0.005 per act-lookup — cost is material for an agent deciding whether to call. It stops short of describing response shape, truncation behavior, or failure modes when an act cannot be resolved.

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 concrete question the tool answers, then the second mode, then audience and price — a sensible ordering with little waste. The 'built for AI agents doing legal and compliance work... without SPARQL' sentence is partly positioning filler, though it does signal the tool replaces raw SPARQL access.

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 10-parameter tool with no output schema, the description covers both modes, the consolidated-version behavior, and cost, while the schema fully documents every parameter. The main gap is that with no output schema, an agent gets no sense of the response structure (how article text, in-force dates and amendment lists are composed) or how maxTextChars truncation manifests.

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%, so every parameter already carries its own explanation and the baseline is 3. The description's contribution is framing rather than parameter detail — it ties article, asOf, amendments and the OJ mode into a single narrative, but adds no syntax, defaults, or edge-case meaning the schema does not already state.

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 names a specific verb-and-resource pair (retrieve article text, in-force status and amendments for an EU act from EUR-Lex) and spells out a second, distinct mode (Official Journal L series listing). It is unmistakably an EU-law tool, which implicitly separates it from national_law_lookup, but it never names or contrasts with that sibling explicitly.

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 two operating modes are described clearly enough that an agent can infer that supplying ojSince switches to OJ listing, and the framing question ('what does Article 50 of the AI Act say today...') gives a concrete use case. There is, however, no explicit when-not-to-use guidance and no routing advice versus national_law_lookup or us_federal_rules for cross-jurisdiction questions.

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