Vorsorge-Regeln

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

Annotations already establish a safe, idempotent, closed-world read, so the lower bar is appropriate; the description adds real scope context the annotations cannot: results are expressed as fractions and percentages with the relevant paragraphs, and coverage halts at the third order. It does not discuss error/edge behavior, but the scope disclosure is substantial.

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?

It is front-loaded with triggers first, then returns, then input constraints and limits, so an agent can decide fast. It is a dense single block and slightly long, but no sentence is 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 an output schema present, the description needn't spell out return values, yet it still names the output shape (fractions, percentages, paragraphs). Annotations cover safety, the schema covers the six parameters, and the description covers eligibility scope and boundaries — nothing an agent needs is missing.

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 baseline 3 applies, but the description goes further by constraining the input space to marital status, matrimonial property regime and the count of living relatives, and explicitly forbidding name collection. That clarifies the intent behind the conditional parameters even if the per-field gating stays in the schema.

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 pairs an explicit action (calculate statutory inheritance shares and Pflichtteil) with the exact resources and even the governing BGB paragraphs. Quoted trigger phrases make it unmistakable which queries this tool answers, and the sibling tools (notary costs, emergency folder) are obviously unrelated.

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 states concrete when-to-use triggers ("Wer erbt ohne Testament", "Pflichtteil berechnen") and an explicit when-not/do-not constraint: never ask for names, only status/regime/number of relatives. The stopping condition (third order) tells the agent when this calculator no longer applies.

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 cover the safety profile (readOnly, idempotent, non-destructive, closed-world), so the bar is lower. The description still adds real context: the legal basis and 2025 amendment, that VAT is 19% and postage is Nr. 32005 KV, and that wills additionally include a cost comparison — none of which is derivable from the annotations.

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 use case and followed by scope and the data-minimization rule. The list of example queries is long but directly supports trigger matching; the enumeration of fee components partly duplicates what the output schema would reveal, which is the only waste.

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 explained, yet the description still names the computed components for predictability. Legal basis, input minimality, and the extra will-comparison behavior are all covered — nothing an agent needs to invoke this correctly is missing.

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?

With schema coverage at 100% and the enum fully documented inline, the schema already carries the semantic load, so baseline 3 applies. The description only restates that document type and an amount suffice and hints at the business value concept; it adds little beyond the existing parameter descriptions.

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+resource: computes German notary fees under GNotKG Tabelle B from document type and asset value. Lists exactly which outputs are produced (fee rate, minimum fees, postage flat rate, VAT, total) and adds a comparison feature for wills, so an agent can tell it apart from erbquoten_berechnen or vorsorge_fakten without opening any 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?

Opens with an explicit trigger condition ('Use when someone asks what a German notary charges for a will or a power of attorney') backed by five realistic phrasings. Also gives a negative constraint — never ask for a name or personal details — and states the minimal input needed, which removes the main failure mode for this tool.

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 cover the safety profile (readOnlyHint, idempotentHint, destructiveHint=false, openWorldHint=false), and the description adds genuinely new behavior: the register is a fixed set of 55 official folders, the returned fields (publisher, pages, fillable PDF, direct PDF link, check date), and the fallback behavior when nothing matches (states covered plus Federal Ministry of Justice nationwide forms). That fallback disclosure is exactly the kind of context annotations cannot carry.

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 usage trigger and resource scope are front-loaded, and the example queries plus the no-match fallback sentence both earn their place. It runs long in a single dense block and could be split, which keeps it just under the top mark.

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, yet the description still gives a compact inventory of what the register returns and what happens on a miss, so an agent knows both the input contract and the failure path. Nothing needed to call this correctly is missing.

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 would be 3, but the description adds a useful constraint the schema does not: 'Needs only a place name or a state.' With zero required parameters, this tells the agent that either field alone suffices and both are not needed, which resolves a real ambiguity.

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 ('free emergency or estate planning folder ... from their district, city or state in Germany') and names the underlying register of 55 official folders on vorsorge-regeln.de. This is clearly distinguishable from the sibling tools, which are calculators (erbquoten_berechnen, notarkosten_berechnen) and a facts lookup (vorsorge_fakten).

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?

Gives explicit activation context ('Use when someone looks for...') plus three realistic example phrasings, which is strong routing guidance. It stops short of naming a sibling or stating when NOT to use it, so it earns a 4 rather than a 5.

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 readOnlyHint=true, idempotentHint=true, openWorldHint=false and destructiveHint=false, so the safety profile is covered. The description adds meaningful provenance behavior: every fact carries a legal source, an official link, and the date it was checked.

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 description is front-loaded with the usage instruction and then lists concrete fact categories. It is somewhat dense and the final topic list duplicates the schema enum, but every element contributes to routing and none is misleading.

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 one required enum parameter and an output schema, the description does not need to explain return values. It supplies enough topic coverage and provenance context for an agent to invoke the tool correctly; only explicit sibling routing is missing.

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% and the single parameter is an enum whose values are already documented in the schema. The description repeats the topic list, which helps confirm routing but does not add syntax or interpretation beyond the schema baseline.

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 specific resource and scope: German fees, deadlines and rules on estate planning documents and inheritance. It enumerates concrete facts (Vorsorgeregister fees, § 7 BtOG certification, BMJ forms, inheritance tax allowances, etc.), making it clearly distinguishable from calculation-oriented siblings such as erbquoten_berechnen and notarkosten_berechnen.

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 explicitly tells the agent to use this instead of answering from memory, which is a strong usage directive. It does not name sibling tools or state exclusions, but the factual-lookup vs. calculation distinction is clear from the purpose.

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