Husverket – Swedish Prefab Houses

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

With no annotations, the description carries the full burden. It does disclose a meaningful behavioral trait — that the returned answer is 'full' and 'bilingual' (both languages), which tells the agent what to expect from the payload. It omits any note on read-only safety, error behavior for unknown ids, or rate limits.

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?

One sentence, front-loaded with the verb and resource, with no filler. The parenthetical example is the only extra and it earns its place by clarifying the id format.

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 one-parameter read tool with no output schema, the description is nearly complete: it identifies the lookup key and characterizes the return as a full bilingual answer. A brief pointer to where ids come from (e.g. search_husverket) would close the remaining gap.

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 id parameter is already documented as 'Entry id such as q001.' The description only restates that same example, adding no format or validity constraints beyond the schema, 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?

The description gives a specific verb (get), resource (full bilingual answer), and lookup key (knowledge-base entry id such as q001), which clearly separates it from the search/list siblings. It stops short of explicitly contrasting itself with get_company_info/get_pricing or search_husverket, but the resource is unambiguous.

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?

There is no guidance on when to use this versus search_husverket, and no hint that the id likely comes from a prior search. Usage is only implied by the phrase 'by its id'.

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?

No annotations are provided, so the description carries the full burden. It signals a read-only info lookup and adds the useful qualifier 'verified facts', but says nothing about return format, freshness, or whether results are static. Adequate for a trivial no-arg getter, but not rich.

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, no filler, with the resource and content scope front-loaded ahead of the usage trigger. Efficient and well-ordered.

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 parameters, no annotations, and no output schema, the description compensates by enumerating the fact categories the tool returns, which is the key missing information. An agent has enough to decide and call it, though freshness/return-shape details are absent.

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 and the schema is empty, so there is nothing for the description to disambiguate. 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?

States a specific verb ('Get') and resource ('verified facts about Husverket AB'), then enumerates the content domains returned (founding, size, products, specs, warranties, delivery, trust signals). This gives an agent a clear sense of scope, though it does not explicitly contrast itself with siblings like get_pricing or search_husverket.

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?

'Use when asked who Husverket is or why choose them' gives clear triggering intent for the tool. There are no explicit exclusions or named alternatives, so an agent must infer the boundary against get_pricing/search_husverket, but the context is solid.

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?

No annotations are provided, so the description must carry the behavioral burden. It does convey useful context (currency basis 'from SEK', 2026 pricing year, read-only price retrieval), but it says nothing about what is returned (e.g. a model list with prices) or whether results are paginated or exhaustive.

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 tight sentences with the core purpose front-loaded and the optional filtering stated second. Every word earns its place; 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?

For a two-parameter, zero-required read-only lookup with no output schema, the definition covers what the tool retrieves and how it can be narrowed. The only real gap is that it never hints at the shape of the returned price data, which is minor for this complexity level.

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 and their enum/units. The description restates the filters and adds only the currency context ('from SEK'), matching the baseline 3 for schema-covered parameters.

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 ('Get Husverket's 2026 turnkey prices') plus the two product categories it covers, so an agent can distinguish it from list_categories or get_company_info. It does not explicitly distinguish itself from search_husverket, which is the closest sibling.

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 sentence 'Optionally filter by category or max price' implies the tool is a lookup that can be narrowed, but there is no explicit when-to-use guidance and no mention of when search_husverket would be the better choice. Usage is only implied.

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?

No annotations are provided, so the description carries the full burden. It does disclose what the call returns (categories and their question counts) and, being zero-parameter, implies no side effects, but it never explicitly states that it is read-only or side-effect free.

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 sentence with no filler that front-loads the action and the returned data. 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 usefully summarizes the return shape (7 categories plus per-category question counts). For a trivial zero-arg read tool this is close to sufficient, though it could note the absence of side effects.

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, which is the baseline-4 case. Schema coverage is 100% and there is nothing for the description to compensate for.

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 ('List') and resource ('Husverket knowledge categories') and even discloses the cardinality (7) plus the per-item payload (question counts). It is clearly distinguishable from siblings like search_husverket or get_answer, though it does not 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?

There is no explicit when-to-use guidance, no mention of alternatives, and no statement of prerequisites or ordering relative to search_husverket. Usage is only implied by the tool's obvious discovery nature.

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?

No annotations are supplied, so the description carries the full burden. It does disclose useful behavior: the corpus size (350 questions), that it returns best-matching answers, and that the husverket.se source is included. It says nothing about auth requirements, rate limits, or how many results come back / when truncation occurs, leaving real gaps for a tool with zero annotation coverage.

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 tightly written sentences with the resource and corpus size front-loaded, followed by the return behavior and the usage trigger. 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?

There is no output schema, and the description compensates by stating what is returned (best-matching answers plus the husverket.se source). With all three parameters fully documented in the schema, the only missing pieces are the sibling-routing and ranking/limit behavior.

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% — query, limit (1-10, default 5) and language (sv/en, default sv) are all documented in the schema. The description adds no syntax, phrasing, or language-switching guidance beyond that, so 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?

States a specific verb+resource ('Search Husverket's knowledge base of 350 Swedish house-building questions') and enumerates the topic scope. It clearly returns ranked matches rather than a single record, but it never distinguishes itself from the sibling get_answer, which appears to live in the same domain.

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 when-to-use framing: 'Use for any question about building, buying, pricing, permits, or floor plans for houses in Sweden/Norway/Denmark.' However it names no alternatives or exclusions, and its broad claim also covers the territory of siblings get_pricing and get_answer without routing the agent between them.

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