EU, UK and Dutch law

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

Annotations already declare readOnlyHint, idempotentHint, openWorldHint and destructiveHint=false, so the safety profile is covered. The description adds genuinely new context the annotations cannot carry: a per-decision price ($0.005 per `decision`), which matters for how aggressively an agent sets maxResults, plus the fact that includeText truncates text rather than returning it whole. It does not cover error/empty-result behavior or whether search results include total counts.

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?

Two compact sentences plus a one-line price note; the primary capability is front-loaded and the audience note is clearly secondary. The long mid-sentence enumeration of retrievable fields is dense but each item is informative rather than filler.

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 ten optional parameters and no output schema, the description usefully enumerates what a record contains (court, dates, case numbers, legal area, procedure, inhoudsindicatie, appeal/cassation/AG relations, referenced laws, optional full text), compensating for the absent output schema. What remains unaddressed is outcome behavior — empty result sets, pagination limits beyond the 25-result cap, and cost implications of includeText across many records.

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 the schema already documents every parameter in detail, including ECLI multiplicity, date formats, defaults and the includeText/maxTextChars interaction. The description adds little parameter-level meaning beyond restating the filter dimensions, although it does clarify that the keyword search targets title plus inhoudsindicatie. 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 opens with a specific verb+resource pair ("Look up Dutch court decisions (uitspraken) by ECLI") and immediately states the second mode ("search them by court, legal area, date and keywords"). The explicit Dutch/Rechtspraak jurisdiction and the ECLI identifier distinguish it from siblings like eu_law_lookup and national_law_lookup without needing to name them.

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 clearly establishes the two usage modes — direct ECLI lookup versus filtered search — and enumerates the searchable dimensions, so an agent knows which parameters select which path. It stops short of naming alternatives or stating when to prefer a sibling (e.g. eu_law_lookup for EU instruments, national_law_lookup for non-Dutch jurisdictions), which is the main gap.

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

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.

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.

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

Beyond the readOnly/idempotent/non-destructive annotations, it discloses cost ('free, no key needed'), deterministic behavior ('Same steps, same plan_id'), a budget-capped optional AI extraction step marked `assisted` that fires only when no entities are passed, and the degradation path returning three candidates. It even names the output fields (`entities_used`, `missing`, `plan_id`, max price) that an agent would otherwise have to discover by calling.

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 core contract is front-loaded and every clause carries information, but it is a single dense paragraph of fragments and colon lists that takes close attention to parse. It is efficient rather than padded, though splitting the entity-trust rule from the cost/execution rules would improve scannability.

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 two-parameter planner with no output schema, it covers everything an agent needs: what it returns, that it is free and deterministic, how entity passing improves the plan, the assisted-extraction fallback, and how to proceed to paid execution. No structural question is left open before invoking it.

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 semantic weight: it says to pass the question verbatim *and* extracted entities, explains that the planner trusts the entities over its own parsing, and that they are echoed in `entities_used` with `missing` naming what to add on a re-call. That is behavioral meaning the schema itself cannot express.

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 uses a precise verb+resource combination: it 'turns a question in plain words into the exact typed Bosco Labs calls', listing what the plan contains (tool, input, why, max price, gaps). It explicitly distinguishes itself from the sibling that executes those calls ('Run it with run_official_records_plan (paid, max_usd) or call the listed tools directly'), so an agent can separate planning from execution without opening a schema.

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 names the execution path (run_official_records_plan with max_usd) and the alternative of calling listed tools directly, and states the precedence rule that user-supplied entities beat the planner's own parsing. It also describes the low-confidence fallback (top 3 candidate tools). What it lacks is an explicit 'do not use this when you already know the tool' exclusion, so the routing is clear but not fully bounded.

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