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

Annotations already indicate read-only, idempotent, and non-destructive behavior. The description adds meaningful context beyond annotations: the exclusive entry via UID for legal entities, the intentional absence of person search, the return ordering (newest first), and the fields returned (date, rubric, title, ID). The 'README Data Protection & Scope' reference further clarifies scope limitations.

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 well-structured with a one-sentence summary, a contextual paragraph, and clearly labeled Args/Returns sections. It is moderately verbose but every section adds value. The README reference is a slight extra but is acceptable for scope clarification.

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?

The description covers the main functional aspects: input requirements (only UID entry), optional filters, output format options, and return contents. An output schema exists, so detailed return types are not required, and the description provides a high-level summary of the returned data (date, rubric, title, ID). It does not elaborate on error handling or edge cases, but that is not critical for this 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?

Although schema description coverage is 0% for the top-level 'params' object, the description's Args section lists each nested field with inline explanations (e.g., uid required and regex-validated, limit range, date format, response_format options). The schema itself also has detailed per-property descriptions, but the tool description enriches this with usage-oriented context, such as 'Join-Schlüssel' for uid and the purpose of filter fields.

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 opens with a specific verb+resource statement: 'Alle Amtsblatt-Publikationen (SHAB + kantonal) zu einer Firmen-UID' (All official gazette publications for a company UID). It clearly distinguishes this tool from siblings by emphasizing the cross-reference between commercial register and gazette via UID, and explicitly notes that person-based search is not available.

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 explains the core use case (join between Handelsregister and Amtsblatt via UID) and states an explicit exclusion: 'ein Personen-Sucheinstieg existiert bewusst nicht.' It implies that the tool is for when you have a company UID and need its publication history, but does not explicitly name alternative tools for other entry points. This is clear context without fully explicit when-to-use vs 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?

The description enriches the annotations by revealing defensive parsing, best-effort handling of additional fields, and required response fields (meta, publicationText, plus company for HR rubrics). This goes beyond the readOnly/idempotent hints and sets expectations for output variability and edge cases.

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 compact and structured with an Args/Returns layout. It includes a valuable 'Quirk' note about the list API, which is high-signal. Slight verbosity in the German phrasing but every sentence contributes useful information.

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?

This is a simple read-only tool with one required parameter. The description explains the quirky data source, required fields, HR-specific behavior, and return format. Combined with annotations and existing schema descriptions, it provides adequate context for an agent to invoke it correctly. No major gaps are apparent.

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 description lists the two parameters (id and response_format) with brief explanations, but the input schema already describes id with an example and response_format with an enum and default. The description adds no new semantics beyond what the schema provides, so a 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 clearly states the tool's function: retrieving a single publication including its official full text from XML, defensively parsed. It distinguishes itself from sibling list tools like gazette_company_publications by explicitly noting that the list API only provides meta, while this tool fetches the actual content.

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 guidance on when to use this tool: when you need the full text content that the list API omits. It explains the quirk that the actual content is only available via this tool's XML endpoint, giving an implicit use case and alternative. It could be more explicit about when not to use it, but the context is strong.

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 the tool as read-only, idempotent, and non-destructive. The description adds context by specifying which sources are checked and what the output covers (reachability, latency, cache age). It does not mention error conditions or auth, but for a status tool these are less critical. No contradiction with 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?

The description is concise and well-structured with clear sections for status, arguments, and return value. Every sentence adds value, and the format is easy to parse quickly. It is not overly verbose.

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 status tool with strong annotations and an output schema, the description is complete. It covers what the tool does, the parameters, and the return value at a sufficient level. The output schema handles detailed return structure, so the description does not need to elaborate further.

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 low (0%), so the description must compensate. It explicitly names the 'response_format' parameter and lists the allowed values ('markdown' or 'json'), adding clarity beyond the schema's enum. This makes the parameter semantics clear and usable.

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 tool's purpose: checking the status (reachability, latency) and cache age for two specific data sources (Zefix and Amtsblattportal). It uses a specific verb ('Prüft') and resource, and it clearly distinguishes itself from sibling tools that search or retrieve company/publication data.

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 a clear use case: when you need to check upstream reachability or cache age. It does not explicitly mention alternatives or when not to use it, but the context of the sibling tools makes this distinction obvious. A 4 is appropriate because the usage context is clear though not fully 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 declare readOnlyHint=true, destructiveHint=false, idempotentHint=true, which the description supports by stating it retrieves data. The description adds detail about the returned data, which is consistent. No contradictions.

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 concise and front-loaded with the main purpose. However, the format mixes paragraphs and bullet points in a single block, which could be better structured for readability.

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?

The description covers the tool's purpose, parameters, return content, and relationship to sibling tools. It lacks error handling or invalid input behavior, but for a simple read-only retrieval tool, it is fairly complete.

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?

Despite the context indicating 0% schema description coverage, the tool description explicitly explains both parameters (ehraid and response_format) in the Args section, adding meaning beyond the schema. The description compensates well for the low coverage.

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 tool retrieves full company details from the commercial register using the internal EHRAID. It lists the returned fields (name, UID, legal form, etc.) and distinguishes from sibling tools by specifying that the EHRAID comes from zefix_search_companies or zefix_get_company_by_uid.

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 indicates when to use this tool (when you have an EHRAID) and explains that the EHRAID can be obtained from other tools. It does not explicitly state when not to use it, but the context implies alternatives (e.g., zefix_get_company_by_uid).

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 indicate readOnly, idempotent, and non-destructive behavior. The description adds value by stating that the tool returns full company details including EHRAID for follow-up queries, and mentions response format options. No contradictions with 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?

The description is concise (two short paragraphs) with clear sections (Args, Returns). Every sentence is useful, and it is front-loaded with the main purpose. No wasted words.

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 tool's simplicity (one required param, optional format, returns a string), the description covers the essential return content (name, legal form, status, SHAB publications, EHRAID). It could be more complete by mentioning error handling (e.g., if UID not found) but overall sufficient.

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?

Despite 'Schema description coverage' being 0% (meaning the description's Args section compensates), the description fully explains both parameters: uid format with examples and response_format enum values. This is critical for correct invocation and adds meaning beyond 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 clearly states that the tool finds a company by its UID and returns full details, including the UID format and its equivalence to the VAT number. It is specific about the resource (company by UID) but does not explicitly differentiate from sibling tools like zefix_get_company (which likely uses EHRAID) or zefix_search_companies.

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 explains the UID format and what the tool returns, implying it should be used when the user has the UID. However, it does not provide explicit when-not-to-use guidance or mention alternatives (e.g., using zefix_get_company for EHRAID-based queries).

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 indicate read-only, non-destructive, idempotent behavior. The description adds value by listing common legal form IDs and their mappings, and explaining the return format, providing additional context beyond 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?

The description is concise and well-structured: first states purpose, then usage context, then parameter details. Every sentence adds value with no 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?

Given the tool's simplicity and the presence of annotations and schema, the description is complete. It explains the return value (all legal forms with ID, name, short form) and the purpose, meeting all informational needs for an agent.

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 description explains both parameters (language and response_format) including their types, defaults, and allowed values. Although the schema already includes descriptions, the description adds clarity and context, complementing the schema fully.

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 it lists all legal forms used in the Swiss commercial register. It also explains its utility for obtaining legalFormId values for filtering in a sibling tool, distinguishing it from other tools.

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 explicitly states it is useful for determining legalFormId values for filtering in zefix_search_companies, providing clear guidance on when to use this tool. It could have mentioned when not to use it, but the guidance is sufficient.

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?

With readOnlyHint, idempotentHint, and destructiveHint all set, the annotations already cover the mutation and safety side. The description adds critical behavioral detail: `legalSeatId` matches the BFS-ID column, not the internal ID, values overlap so the wrong ID silently produces a real but wrong municipality, and the tool performs the resolution itself. It also states 'genau eine Gemeinde' for legal_seat_id and '~2.100 Gemeinden' without filters. The only real gap is the unspecified precedence when both `legal_seat_id` and `canton` are passed.

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 well structured: a one-line purpose, a necessary warning paragraph, then a compact Args/Returns section. The longer warning is fully justified because it prevents a silently incorrect lookup, and no sentences are wasted. The formatting with backticks and line breaks makes it easy to scan.

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 does not need to enumerate the return values in detail, but custom level covers name, canton, BFS-ID and Handelsregisterkreis-ID anyway. It handles the main semantic trap, and it outlines the behavior for the relevant input patterns. It is not complete on the boundary case of combining `legal_seat_id` and `canton`, and it could better point to the sibling tools that produce produce `legalSeatId` (zefix_get_company, zefix_search_companies).

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 schema already describes each nested parameter, so the description does not need to start from zero. It adds value with the concrete warning about BFS-ID vs ID, the 'genau eine Gemeinde' consequence, and the meaningful examples for `canton`. The only missing semantic layer is explanation of parameter compatibility or precedence when multiple arguments are provided at once.

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 opening sentence names a specific verb and resource: 'Listet Schweizer Gemeinden auf und löst die `legalSeatId` einer Firma auf.' It also immediately distinguishes the critical semantic mismatch between BFS-ID and internal ID, which makes the tool's purpose much clearer. This separates it naturally from sibling tools that focus on companies rather than on the lookup/resolution side.

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 concrete context about parameter usage: legal_seat_id resolves exactly one Gemeinde, canton filters the list, and no filter returns about 2,100 municipalities. But it does not explicitly say when to choose this tool over its siblings, nor 'when not to use it'. It also leaves ambiguous how `canton` and `legal_seat_id` should be combined if an agent passes both.

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, destructiveHint, idempotentHint, and openWorldHint. The description adds behavioral context about pagination info and response format, which goes beyond annotations. No contradictions found.

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 well-structured with a headline, summary, and clear Args/Returns sections. It front-loads the purpose. Slightly verbose but efficient with no wasted information.

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?

The description covers purpose, parameters, returns, and usage context. It mentions pagination and response format options. However, it omits error conditions or rate limits. Given the output schema and annotations, it is fairly complete.

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 input schema provides detailed descriptions for each parameter. The description's Args section repeats and slightly augments this (e.g., referencing zefix_list_legal_forms for legal_form_ids). Since schema coverage is effectively high, the description adds marginal new meaning.

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 it searches for companies in the Swiss commercial register by name, canton, and legal form. It uses a specific verb-resource combination and distinguishes from sibling tools like zefix_get_company and zefix_verify_company.

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 suggests ideal use cases (supplier checks, contract screenings, procurement due diligence) but does not explicitly mention when not to use it or compare with alternatives. The context signals list siblings, but the description lacks that comparison.

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, destructiveHint=false, idempotentHint=true, and openWorldHint=true. The description adds behavioral context by listing what the tool checks (registration, status, legal form, domicile, similar companies) and that it returns a yes/no answer plus basic details. This aligns with annotations and adds value beyond them.

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 concise, starting with the core question, followed by a clear list of checks and parameter details. Every sentence serves a purpose, with no unnecessary fluff. The structure is front-loaded and easy to parse.

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 tool's simplicity and the presence of annotations and a likely output schema (not shown), the description covers the essential aspects: purpose, usage scenario, checks performed, and parameter hints. It could mention the output format more explicitly, but the return value description suffices.

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 input schema provides descriptions for both parameters in English, while the tool description echoes them in German. Although schema description coverage is reported as 0% (possibly a context issue), the description adds minimal new meaning beyond the schema. It provides German translations and constraints (min 3 chars for name) but does not significantly enhance understanding.

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 tool's purpose: a quick verification of whether a company is registered and active in the commercial register, returning a yes/no answer and basic details. It distinguishes from sibling tools like 'zefix_search_companies' or 'zefix_get_company' by emphasizing its speed and focus on a binary check.

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 explicitly recommends using this tool as a first check before contracts, procurement, or subsidies, providing clear usage context. It does not explicitly state when not to use it or alternatives, but the context implies it is for quick checks rather than detailed lookups.

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