RAFSOFT.NET — Faktura VAT

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

Annotations already declare the tool as read-only and idempotent, so safety is covered. The description adds valuable behavioral context beyond annotations by clarifying the pricing model (PLN net, one-time purchase, no subscription) and the scope of the feature matrix, which helps the agent set expectations about the returned information.

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 a single, compact sentence that front-loads the core purpose before elaborating on what is compared. Every phrase adds useful detail (editions, currency, one-time purchase, feature categories), with no filler or redundancy.

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 read-only comparison tool with a fully documented schema and safety annotations, the description is largely complete: it states what is compared, the pricing terms, and the feature areas covered. It does not describe the exact output structure, but the absence of an output schema is mitigated by the explicit mention of prices and a feature matrix.

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 both parameters ('editions' and 'onlyDifferences') adequately. The description reinforces the edition names but adds no meaning beyond the schema, so the baseline score of 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 specific verb ('Compare'), a precise resource ('Faktura VAT 2027 editions'), and enumerates the exact editions (START, STANDARD, PRO). It also specifies the comparison dimensions (prices and feature availability matrix), making it clearly distinct from sibling tools that focus on FAQs, KSeF info, product info, or knowledge base searches.

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 provides clear context for when to use the tool: whenever an agent needs to compare editions of Faktura VAT 2027. It does not explicitly name alternatives or state when not to use it, but the sibling tools serve obviously different purposes, so an agent can infer the right selection without ambiguity.

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, openWorldHint, idempotentHint, and non-destructive behavior, so the safety profile is covered. The description adds useful content context by listing sources and sections, but does not disclose return format, pagination, or behavior when no section is provided. This is acceptable given the annotations, but no significant extra behavioral detail is added.

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 tool's core purpose and then efficiently lists the relevant sources and sections. The section enumeration is somewhat long but directly useful for parameter selection, and no unnecessary filler is present.

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?

Given low complexity, full schema coverage, and rich annotations, the description is largely complete for calling the tool correctly. It covers content type, language, sources, and sections. It lacks explicit comparison to sibling tools, but this is more a usage-guidance gap than a completeness gap for basic invocation.

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% for both parameters, so the schema already documents source and section. The description adds meaningful value by enumerating the exact section names per source, helping an agent construct valid section substring filters beyond the schema's generic 'Case-insensitive substring filter on section name'.

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 clearly identifies the tool as retrieving FAQ content for Faktura VAT, specifically Polish question/answer pairs, and enumerates the available sources and sections. This distinguishes it from sibling tools like get_ksef_info or search_knowledge_base, which target different resources.

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 provides no explicit guidance on when to use this tool versus alternatives such as search_knowledge_base or get_ksef_info. The source/section structure implies filtering use, but there is no stated selection criteria or exclusionary context.

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, openWorldHint=true, idempotentHint=true, and destructiveHint=false, fully covering the safety profile. The description adds no additional behavioral context such as response format or pagination, but it does not contradict the annotations either.

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?

A single, front-loaded sentence that identifies the tool and densely lists its coverage areas. Every phrase contributes value; there is no filler or redundancy.

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 info tool with one optional enum parameter, the description adequately conveys the scope. However, it does not clarify the output format or how to differentiate from the overlapping get_faq sibling, leaving some contextual ambiguity for agents.

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 optional 'topic' parameter has a descriptive enum with per-value explanations. The description reiterates those topics in prose but does not add new syntactic or semantic details beyond the schema, so the baseline of 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 clearly identifies the resource ('KSeF 2.0 info') and enumerates specific content areas: integration, supported invoice types, FA(3) validator, KSeF Client features, and FAQ. It is specific enough to distinguish the tool from generic info tools, but it does not explicitly separate itself from the overlapping sibling get_faq.

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 listed topics, suggesting agents should call this when KSeF integration information is requested. However, there is no explicit when-to-use or when-not-to-use guidance, and the description does not mention alternatives like get_faq or search_knowledge_base, despite clear overlap with get_faq's FAQ scope.

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?

The annotations already declare readOnlyHint, idempotentHint, destructiveHint=false and openWorldHint, so the safety profile is covered without the description's help. The description does add useful domain context about what data is returned (current Windows versions 2026/2027, PLN pricing), but says nothing about freshness, localization limits, or failure modes for unavailable products.

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?

A single front-loaded sentence with no filler; every clause adds concrete content. The nested parenthetical is dense but still readable and wastes nothing.

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 read-only, single-optional-param lookup with no output schema, the description adequately conveys the scope of returned data. The only gap is that it does not describe how the optional 'section' parameter changes the response payload.

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 'section' enum is fully documented with the default, so the baseline is 3. The description hints at section content groupings (pricing/downloads/mobilna) but does not map them to the parameter or explain what 'all' vs 'mobilna' returns.

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 gives a specific verb and resource ('Returns product and pricing info') and enumerates the concrete contents (plans, PLN prices, download URLs, purchase links) for two named products. It is clear on its own, but it never positions itself against siblings such as compare_editions or get_faq, so sibling differentiation is left to inference.

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?

No when-to-use or when-not-to-use guidance is given, and no alternative is named. An agent looking for a feature comparison could plausibly land here instead of compare_editions with nothing in the description to steer 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?

Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, covering safety and side effects. The description adds the BM25 algorithm and the knowledge base scope, which provides some behavioral context beyond the annotations (e.g., that it is a free-text search). However, it does not disclose details like result ordering, pagination limits, or error behavior, which are not covered by annotations. Given the annotations cover the critical safety profile, a 3 is appropriate.

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 a single, well-structured sentence with no redundancy. The primary action ('BM25 full-text search') is front-loaded, followed by scope and domain. Every word adds value, and there is no extra fluff or repeated information from the schema.

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 search tool with only two parameters, both fully documented in the schema, and annotations covering safety and idempotency, the description is complete. It specifies the search algorithm, the corpus (knowledge base sections), and the domain. No additional context (like return format) is necessary since this is a standard search operation and no output schema exists.

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%, with both parameters (query and topK) already documented in the schema. The description adds minor context by specifying the query language (Polish or English) is already in the schema, and the BM25 algorithm implies free-text input. This adds a little meaning (free-text vs exact match) but does not substantially compensate beyond the schema. Baseline 3 is correct.

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 clearly states the verb (search), the resource (rafsoft.net knowledge base), and the scope (FAQ, docs, blog, pricing). It also specifies the domain (Faktura VAT Polish invoicing software). This distinguishes it from siblings like get_faq (targeted FAQ retrieval) and get_product_info (specific product details). An agent can immediately understand what this tool does and how it differs.

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 provides clear context: it is a full-text search over a knowledge base, implying use for open-ended queries rather than known-item lookups. However, it does not explicitly mention when not to use it or reference sibling tools (e.g., use get_faq for a specific FAQ entry). The context is clear but lacks explicit exclusions or alternatives.

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