AZAV-Doku

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

Annotations already declare readOnlyHint=true, idempotentHint=true, destructiveHint=false and openWorldHint=false, so the safety profile is covered. The description adds real behavioral context beyond that: the derived rules (5 Werktage für den Bericht, Feiertage des Bundeslands, unverzüglich bei Nichtantritt/Abbruch, Ausschlussfrist § 326 SGB III) and the fact that a legal basis plus source URL is returned.

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 verb and resource are front-loaded, and the enumerated deadline list is dense but each item carries information about what is computed. The only waste is the trailing English sentence, which largely duplicates the German content.

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 need not explain return values, and it still usefully flags the computed deadline set and the holiday-dependence on Bundesland. The only gap is the absence of any when-to-use guidance, which is minor for a single-purpose calculator.

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 each parameter (including the enum meanings and the 'Ohne Angabe: Feiertage nicht berücksichtigt' default) is already fully documented in the schema. The description only restates the optional parameters in parentheses and adds no syntax, default, or interaction detail beyond it — the baseline 3 applies.

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 precise verb+resource ('Berechnet alle Fristen eines AVGS-Teilnehmers (§ 45 SGB III) aus Teilnahmeende') and enumerates the concrete deadline types produced. It is clearly distinct from the sibling tools (ba_formulare, bdks_pruefen, glossar), none of which compute deadlines.

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 implied by the input contract (Teilnahmeende required; Beginn/Abbruch/Bundesland optional) and the tool's scope, but the description never states when to reach for this tool versus alternatives, nor any exclusions or prerequisites. Adequate but leaves routing to inference.

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, destructiveHint=false and openWorldHint=false, so the safety profile is fully covered. The description adds useful context about the metadata each entry carries (Version, Zweck, Frist, Empfänger, PDF-URL, Online-Ausfüllen-Link), but since an output schema exists, this return-content detail is partly redundant and adds limited behavioral depth.

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 German sentence front-loads the resource and enumerates forms well, but the closing English sentence ('Lists the official German employment agency forms for AVGS providers') restates the opening and does not earn its place. The parenthetical list of metadata fields is dense but relevant.

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 simple read-only listing tool with one optional enum parameter, an output schema and full annotation coverage, the description is essentially complete – the agent knows what categories exist and what each entry contains. Only sibling differentiation 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 description coverage is 100% and the single `formular` parameter is a fully documented enum, so the schema does the heavy lifting. The description mentions the form categories that correspond to the enum values but adds no filtering semantics beyond what the schema already provides – the baseline 3 applies.

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?

Names a specific resource (official Bundesagentur für Arbeit forms for AVGS measures under § 45 SGB III) and enumerates the exact forms returned (Teilnahmebezogener Bericht, Fehltage, AMDL, § 16k Bericht). The purpose is unambiguous, but it never distinguishes itself from the sibling tools (avgs_fristen, bdks_pruefen, glossar), so an agent must infer the routing 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?

The description states what the tool contains but gives no when-to-use guidance, no mention of the optional `formular` filter's role in usage, and no exclusions or alternatives relative to the sibling tools. An agent has no textual signal for choosing this over glossar or avgs_fristen.

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, idempotentHint, destructiveHint=false and openWorldHint=false, so safety is covered. The description adds real behavioral context beyond that: it discloses that the tool compares a supplied rate against the 25-%-Grenze and reports the change versus 2024, which is the actual logic an agent needs to trust the result.

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 dense but front-loaded: the lookup scope comes first, the optional check second. The German and English sentences partially duplicate each other, but the bilingual phrasing serves retrieval, and no sentence is pure 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 a full output schema, the description need not explain return values, and it does cover the eligible Nr. categories, measure type, and the optional rate-check path. Only the fallback behavior when neither kostensatz nor gesamtkosten is supplied is left implicit.

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 enum meanings for 'art' and 'ziel' and the numeric bounds are already fully documented in the schema. The description only restates which fields exist and that 'teilnehmende' is group-only, adding no syntax or edge-case meaning beyond the schema — baseline 3 applies.

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 resource (B-DKS 2026 Bundesdurchschnittskostensatz per Maßnahmestunde) and a specific action (lookup plus rate check), and scopes it to § 45 SGB III Nr. 1/4/5 and Einzel-/Gruppenmaßnahme. None of the siblings (avgs_fristen, ba_formulare, glossar) overlap with cost-rate lookup, so the agent can route unambiguously.

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 signals the conditional branch — the lookup is the default, and 'Optional: eigenen Kostensatz oder Gesamtkosten + Stunden (+ Teilnehmende) prüfen' tells the agent when to supply the optional parameters. However, it never states when NOT to use this tool or which sibling to reach for a deadline/form/term question, so usage is implied rather than explicit.

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). The description adds real behavioral context beyond them: results include a source and a link, and omitting the term switches to a full list. It says nothing about behavior for an unknown term, which is a minor gap.

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?

Very short and front-loaded, with the core purpose first and the no-argument case next. The trailing English sentence partially restates the German opening, a small amount of redundancy that keeps it from a 5.

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 single-parameter, annotation-covered, no-output-schema tool, the description covers purpose, input semantics, and what is returned (term, source, link), which is enough to call it correctly. Only the unknown-term behavior is left unstated.

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 is 3, but the description adds meaning the schema does not: the parameter is optional and its absence produces a complete list of terms, and it restates the concept with a worked example ('B-DKS'). This genuinely aids correct invocation.

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 ('Erklärt') and a precisely scoped resource (Fachbegriffe rund um AVGS, AZAV und § 45 SGB III) with concrete examples, and explicitly notes the no-argument mode. This is clearly distinguishable from siblings like avgs_fristen, ba_formulare and bdks_pruefen.

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?

'Ohne begriff: Liste aller Begriffe' tells the agent exactly how to invoke the tool for lookup vs. enumeration, which is the main usage decision for this tool. It does not name an alternative tool, but none of the siblings appears to overlap with glossary lookup.

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