Commerce OS Integrator

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 useful context about the pricing basis (net PLN, mirrored from a URL), but it does not describe return format or other behavioral traits beyond content scope.

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 two tightly written sentences with the resource and its contents front-loaded. Every phrase adds relevant information without repetition or 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?

For a zero-parameter, read-only price list with rich annotations, the description is largely complete: it says what the price list covers and where the prices come from. It could mention the return shape, but that is a minor gap given the absence of an output schema and the simplicity of the tool.

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?

The tool takes zero parameters, so there is nothing for the description to clarify. The baseline for a parameterless tool is 4.

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 a specific resource: the Commerce OS Integrator price list, including implementation packages, monthly maintenance, and add-ons. It does not explicitly differentiate itself from sibling tools such as porownaj_integratory or oblicz_oszczednosc, but the resource is distinct enough to be understood.

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 only implied by the word 'Cennik' (price list); there is no explicit statement of when to use this tool versus the comparison or savings-calculator siblings. The description gives no when-not conditions or alternative routing.

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 and destructiveHint=false, so the safety profile is covered. The description adds real behavioral context beyond that: the response is full-content Markdown, includes a title and a citation address, and blog articles additionally carry sources. It does not discuss failure modes for an unknown id, but for a read-only fetch this is solid added value.

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: the action and output format come first, then the accepted document kinds. The parenthetical enumeration of page kinds is somewhat dense but every clause carries information. No filler or repetition.

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, return values need no explanation, and annotations cover safety. The description still supplies the essentials an agent needs: what slice of content comes back, the Markdown format, the citation metadata, and the valid id forms. Nothing critical to correct invocation 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 'id' parameter is fully described, so the description carries no additional burden. It restates the same id forms (article slug, page path, or page URL) already enumerated in the schema, adding no new syntax or edge-case guidance. 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?

States a specific verb and resource: returns the full document content (Markdown) for a search result id, and names the two content families it can return (blog article with sources, Integrator page). An agent knows exactly what it gets. It does not, however, distinguish itself from the sibling 'pobierz_artykul', which reads like an overlapping retrieve operation.

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 only implied: the id is described as coming 'z wyniku search', which signals this tool is the follow-up to a search call. There is no explicit when-to-use/when-not framing and no mention of the alternatives (search, szukaj_artykulow, pobierz_artykul), so an agent must infer the routing itself.

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, non-destructive and closed-world, so the safety profile is covered. The description adds the genuinely useful behavioral note that the tool transmits nothing — pre-empting the assumption that a 'contact' tool submits a message or form.

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 short clauses: the returned data is front-loaded, then the non-sending caveat. Every sentence earns its place with no 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 no output schema, the description does the right thing by enumerating the fields an agent will get back. It stops short of saying how they're returned (structure/format), but that is a minor gap for a trivial zero-param lookup.

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?

The tool takes zero parameters, so the schema carries no semantic burden and the baseline is 4; the description correctly offers nothing misleading about inputs.

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 the specific resource it returns (Fide-Soft contact details: email, phone, company address, deployment-form URL) and identifies the vendor/creator, which no sibling does. It's clearly distinguishable from cennik_integratora, porownaj_integratory or the search/fetch tools, though it doesn't name a 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?

Usage is only implied — an agent infers it should call this when the user wants to reach the vendor. The line 'Narzędzie niczego nie wysyła' usefully rules out one misinterpretation, but there is no explicit when/when-not guidance relative to alternatives.

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, non-destructive and closed-world, so the safety profile is covered. The description adds useful context about what the model excludes (no subscription, no per-order fees) and that results mirror the website calculator, but says nothing about precision, rounding, currency, or the >50000-order cut-off (which lives only in the schema).

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 opens with the verb and enumerates the outputs, followed by one short trust clause tying it to the site calculator. Dense but no sentence is wasted; the parenthetical about BaseLinker naming is genuinely useful for disambiguation.

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 no output schema, the description carries the burden of describing returns and does so explicitly: monthly cost, monthly and annual savings, and payback on the implementation package. Gaps remain around units/currency of the returned figures and the upper-bound handling, but an agent has enough to call it correctly.

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, including the enum meanings and the 'bez wartości' defaulting behavior for oferty and pakiet_wdrozenia, is already documented in the schema. The description adds no parameter-level meaning beyond that, which is the baseline-3 case.

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 computation: the monthly cost of the current integrator (Base.com/BaseLinker, Apilo, Sellasist) versus Commerce OS Integrator maintenance, plus monthly/annual savings and implementation-package payback. That is enough to tell it apart from siblings like porownaj_integratory or cennik_integratora, but the difference is left implicit rather than stated.

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 only implied: an agent can infer this is the 'compute my savings' tool while cennik_integratora is the price list, but the description never says so or when not to call it. There are no preconditions or exclusions named, and 'te same wyliczenia co kalkulator na stronie' is context, not routing guidance.

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 and non-destructive, so the safety bar is low; the description still adds real value by enumerating the sections returned (treść, 'W skrócie', FAQ, źródła z datą, powiązane artykuły) and by equating the result with the article's .md URL, which lets the agent predict the payload shape.

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 sentences: the return value and its structure first, the required input second. No filler, nothing repeated from the schema except the input hint, which earns its place.

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?

There is no output schema, so the description carries the return-value burden and does so by listing every section the Markdown contains. With one documented parameter and annotations covering the safety profile, nothing an agent needs 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% and the property description already gives both accepted forms with an example, so the description can only add the provenance hint ('z szukaj_artykulow'). That is marginal beyond what the schema states, so 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 verb and resource ('Zwraca pełny artykuł z bloga commerceos.pl') plus the exact output format (Markdown). It also distinguishes itself from the sibling szukaj_artykulow, which only produces the slug/URL this tool consumes.

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?

Explicitly routes the agent to szukaj_artykulow as the source of the accepted input ('Podaj slug albo adres artykułu z szukaj_artykulow'), giving a clear workflow. It stops short of stating when not to use it or what happens with an invalid slug.

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/non-destructive/closed-world, so the safety profile is covered. The description adds real value beyond that by disclosing the return content: each vendor's price-list URL and the date the price was verified, giving the agent freshness context for citing results.

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 dense sentence with purpose first and return content second; no filler. It is slightly information-packed but every clause earns its place.

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 no output schema, the description compensates by naming what is returned (price-list addresses and verification dates). For a read-only, fully documented 3-parameter tool this is nearly sufficient; only the output shape (e.g. whether all four vendors always appear, currency) 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 schema already explains all three parameters, including the 'oferty' threshold rule. The description references only orders and channels, omitting 'oferty', so it adds no meaning 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?

Names a specific verb ('Porównuje') plus the four exact products being compared and the inputs that drive the comparison. An agent can distinguish this from siblings like cennik_integratora (single price list) or oblicz_oszczednosc (savings) without opening the 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?

The description implies the comparison use case ('przy podanej liczbie zamówień i kanałów sprzedaży') but never states when to pick this over oblicz_oszczednosc or cennik_integratora, nor any exclusions. Usage must be inferred from the tool name and sibling set.

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 establish read-only, idempotent, non-destructive, closed-world behavior. The description adds meaningful context beyond that: the two source domains, a maximum of 10 results, the returned fields, and that full text is retrieved via `fetch`.

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-loads the searched domains, then states result count and return fields, then routes to `fetch` for full content. No sentence is wasted and the parenthetical examples are useful rather than redundant.

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 the annotations, full schema coverage, and an output schema, the description supplies everything an agent needs: scope, result limit, returned fields, and the alternative tool for full content. Nothing material is missing for correct 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?

The single `query` parameter is fully documented in the schema with examples, so the schema carries the parameter semantics. The description does not add syntax, constraints, or interpretation beyond what the schema already provides.

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 search action over two named sources: commerceos.pl blog articles and Commerce OS Integrator pages, with examples of page topics. This is much clearer than a generic search, though it does not explicitly distinguish itself from the similar sibling `szukaj_artykulow`.

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?

Clearly indicates when the tool is useful by scoping the content it searches and by naming `fetch` as the way to get full content. It lacks explicit when-not guidance or direct comparison with siblings such as `szukaj_artykulow` and `pobierz_artykul`.

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, non-destructive and closed-world behavior, so the bar is lower. The description still adds value beyond them: it discloses the exact result shape (title, address, summary, date) and the empty-query fallback to latest articles, which the agent cannot infer from 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?

Three short sentences that front-load the core purpose and then the return shape and edge case; nothing is redundant. The parenthetical topic list is long but earns its place as query-term guidance.

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 2-parameter, zero-required read tool with full schema coverage and safety annotations, the description covers purpose, result fields, and the empty-query case. No output schema exists, but the return values are described inline, so an agent has everything needed to call it correctly.

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 both zapytanie and limit are already documented with examples and bounds. The description's topic list gives some hint about what query terms work, but adds no syntax, matching behavior, or limit semantics beyond the schema — 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?

States a specific verb and resource: searching articles on the commerceos.pl blog, with concrete topic areas (BaseLinkera migration, KSeF, Allegro automations, etc.). It also lists the returned fields (title, url, summary, date), which implicitly separates it from the sibling pobierz_artykul that would fetch full content, though no sibling is named 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?

Usage is implied by the topic list and the note that an empty query returns the newest articles, which is a real usage rule. However, it never states when to prefer this over pobierz_artykul, fetch, or search, nor any exclusions or prerequisites.

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