Handelsregister

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

The description adds substantial behavioral context not available in the annotations: it explains id normalization from bare national ids to prefixed form, that unsupported filters are reported in a notice rather than silently dropped, and that the tool returns no company data. These are meaningful runtime behaviors beyond the readOnly and idempotent hints.

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 longer than typical but well organized with clear sections. It front-loads the core identity and read-only note, then elaborates on parameters and return structure. Slightly dense, but every major point 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?

For a tool with one optional parameter and an existing output schema, the description fully covers behavior, return shape, id normalization, filter handling, and guidance on when to call it. An agent has enough to invoke it correctly without further web searching.

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 0%, so the description must fully compensate. It does: it documents the country parameter's optionality, default value, allowed values ('AT' | 'DE' | 'all'), and exactly what each selection controls. This adds all meaning the bare schema lacks.

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 identifies the tool as a schema self-description resource and explicitly enumerates what it covers: unified id scheme, available filters, per-country capabilities, and per-country field catalogs. This is a specific verb-plus-resource statement that clearly distinguishes it from the data-returning sibling 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?

It gives a clear usage directive: call once up front when unsure which filter or tool to use, and explicitly notes that it returns no company data. However, it does not name specific alternative tools or spell out when to prefer them, so it falls short of a fully explicit routing recommendation.

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 goes well beyond the annotations: it discloses that each call writes short-lived export files, auto-deletes them, provides signed download links valid for ~60 minutes, produces one CSV per country, and notes that DE files lack financial columns. It also explains the semantics only during prep instead of adding a misleading read_only hint. This is robust behavioral disclosure.

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?

Despite being detailed, the description is well-structured: it opens with the clear purpose, labels its main operational restrictions, lists parameters briefly, then describes return structure and usage boundaries. Every sentence adds meaningful information about behavior or an edge case; there is no padding.

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 complexity of creating country-specific CSV exports with transient files, the description covers the full operational surface: output shape, row limit, defaults, file format, and per-country column differences. The annotations and structured schema add further context, making the description complete enough for an agent to invoke 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 0%, so the description needs to be the sole parameter explainer. It succeeds for all four parameters: filters (exact same as search_companies), sort, max_rows (default 1000/max), and country (AT|DE|all). It does not enumerate the filter fields here, instead referring to a sibling schema, but that is a reasonable pointer for a large unified filter object.

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 uses a specific verb ('Export') with a well-defined resource ('matched company set' as CSV files) and explicitly names the AT + DE scope and the downloadable CSV output. It also distinguishes itself from screen-browsing search tools, so an agent can tell this is the export/lead-list tool.

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 says 'For browsing/ranking on screen use search_companies instead', which is a clear alternative. It also clarifies that filters and sort are intentionally shared with search_companies, so use of this tool is well-routed. It could go further by naming other sibling conditions, but the guidance 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?

Beyond the read-only/idempotent/destructive annotations, the description richly explains behavioral semantics: empty peers_home indicates an unknown id or missing ranking data, peers_abroad is a meaning-based rather than financial match, and differing data depth between countries is acknowledged. This goes far beyond what annotations alone convey.

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: purpose and read-only status are front-loaded, then parameters, then return semantics, then routing to alternatives. Although detailed, every sentence adds necessary information rather than padding.

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 three parameters, 0% schema description coverage, and the tool's nuanced cross-border behavior, the description covers all needed information: input format, response envelope, empty-result meaning, and when another tool fits. The agent can make a correct invocation decision without further context.

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 0%, so the parameter section carries full weight. It defines the company_id format with examples, notes that bare national ids are accepted, clarifies n is per country, and explains cross_border's effect on the response. This fully compensates for the schema's lack of parameter documentation.

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 operation and resource: finding companies most similar to a given one, with optional cross-border peers. It distinguishes itself from siblings by describing what it returns and explicitly pointing to search_companies as the strict-filter alternative.

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 explains when to enable cross_border, clarifies that peers_home uses each register's own peer logic, and routes non-peer use cases elsewhere: 'For a strict filtered list use search_companies; for aggregates use the country server's cohort tools.' This is explicit guidance an agent can act on.

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 operation read-only, idempotent, and non-destructive, and the description reinforces this. It additionally discloses important runtime behaviors: unknown ids produce {error: not_found}, DE financial statements must not be reported as zero/missing, and max_signatories behavior differs by country.

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 dense but each sentence contributes necessary operational knowledge. Purpose is front-loaded, parameter details are organized, and country-specific differences are separated clearly, making the long text easy to navigate.

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 that an output schema exists, the description covers everything an agent needs to select and invoke the tool correctly: input derivation, path routing, parameter semantics, per-country return content, known data gaps, and error behavior. Nothing essential 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?

Despite 0% schema description coverage, the description fully documents both parameters. It gives exact formats and examples for company_id, explains how to obtain it, and precisely defines max_signatories defaults, valid values, country restrictions, and ignored cases for AT.

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 profile for exactly ONE company, routed by its unified company_id. It also differentiates itself from siblings by explicitly pointing to search_companies for the case where only a name is known, making the tool's role 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?

Provides explicit direction: use search_companies first when only a name is available, and take company_id from a search card. It also details country-specific behavior and warns that German financial statements are not covered, giving an agent clear guidance on when this tool is and is not appropriate.

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 and idempotentHint, but the description adds valuable behavioral context: it explains countries_unavailable behavior, the backfill caveat for DE counts, and how not to interpret low counts. This clearly exceeds the annotation baseline and helps the agent avoid incorrect conclusions.

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 dense but well-structured: a one-line usage cue, a compact parameter section, and a return-shape explanation. Every sentence adds necessary information, and the critical 'call first' guidance is front-loaded.

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 single optional parameter, the return structure, error handling for unreachable countries, and the meaning of incomplete data. Given the output schema and sibling context already provided, nothing necessary for safe and 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 description coverage is 0%, so the description is the only source of parameter meaning. It explains the country parameter is optional, defaults to "all", and defines the allowed values "AT", "DE", and "all". It also clarifies how the parameter affects the returned payload.

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 returns dataset coverage and a capability matrix per country, which is a specific resource and purpose rather than a tautology. It also distinguishes itself from sibling tools by explicitly routing to describe_fields for filter values and search_companies for per-company 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 gives an explicit directive: 'CALL THIS FIRST before concluding that something does not exist in a country.' It also names alternatives and the conditions under which they should be used, making the selection decision clear.

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?

Read-only is already covered by annotations, but the description adds important non-obvious behavior: default date window, availability differences by country, the 'never as zero' rule for DE, and the top-level return shape. It exceeds annotation coverage without contradicting it.

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?

Four dense sentences, each adding value: the function's result, the parameter list, the availability caveat, and the sibling route. It is front-loaded with the primary purpose and avoids fluff.

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 7-parameter read-only tool with an output schema, this description covers parameter selection, default behavior, availability limitations and where to go for individual events. Nothing about selecting or invoking the tool correctly seems 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?

The input schema has zero parameter descriptions, but the description compensates by listing all parameters, marking them optional, giving the last-30-day default, restricting nace_division and legal_form to AT, and enumerating country values. It falls slightly short only because it does not spell out the expected string format for dates or explain the NACE/bundesland concepts.

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 action and resource: aggregate counts of register changes by type and region per country. It also distinguishes itself from list_events, which is for individual changes, so an agent can select it correctly.

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 explicitly routes the agent to list_events for individual changes and makes the current availability clear: only AT exposes event statistics, while DE reports 'not yet available' instead of zero. This gives both positive and negative usage 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?

Beyond the existing readOnly/idempotent/destructive annotations, the description adds important behavioral context: it only returns the calling key's own usage, never another user's data, never the email behind the key, and it explains that a single meter spans AT and DE as the billing point. This provides meaningful transparency about limits and privacy.

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 and front-loaded: it opens with a clear summary and then provides parameter details and return-scope specifics. It is slightly repetitive around 'own usage' and 'calling key's own usage,' but every section earns its place and nothing is irrelevant.

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 single optional parameter, existing safety annotations, and an output schema present, the description is complete for making a correct call. It states the call filter, the result scope, the billing-meter behavior, and a practical use case, leaving no important operational 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?

The schema provides only the parameter name, type, and default, with no descriptions. The tool description compensates fully by documenting the optional window parameter, its default value of 'today', and every valid value: today, yesterday, month_to_date, last_30_days, and all.

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 precisely what the tool does: obtain the calling API key's own usage, including call count and weighted compute-units, per tool, and it clarifies the 'both registers' scope. It also distinguishes the tool from siblings by emphasizing 'your own' usage and explicitly excluding other users' 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 gives a concrete use case: 'Use it to check your consumption against the plan's rate limits.' It is clear about context but does not explicitly name alternatives or provide when-not-to-use guidance, which keeps it slightly below the top score.

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 provide readOnlyHint and idempotentHint, and the description substantially deepens behavioral context: it explains subset type skipping, per-country feeds, data availability windows so empty stretches are not misread, prefixed company_ids, and before/after values only for detailed AT types. 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 well-organized with a leading purpose sentence, a bulleted parameter list, and a compact return-value explanation. Every sentence or bullet adds essential operational detail without redundancy, making the length justified given the tool's API complexity.

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 output schema exists, the description still provides the important context that can't be inferred from schema: country-specific availability windows, AT/DE type distinctions, company_id constraints, and routing to sibling tools. It leaves the agent a fully operational understanding of when and how to invoke it.

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 0%, and the description compensates fully by documenting every parameter, including the full types superset enum, ISO date defaults, country-specific bounds for nace_division/legal_form, the company_ids AT/DE difference, and pagination defaults. It also states that all parameters are optional and AND-combined.

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 lists cross-company, cross-country register changes, newest first, and labels it as the market-watch/deal-sourcing surface. This goes beyond the title by specifying scope, sorting, and data source, and it is immediately distinguishable from sibling tools that retrieve company details or aggregate stats.

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 directs users to alternatives: 'For aggregate counts use get_event_stats; for one company's history use get_company_details.' It also explains parameter AND-combination semantics and country-specific type behavior, helping the agent decide when and how to call 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 readOnly, idempotent, and non-destructive. The description adds transparency beyond annotations by explaining the optional 'cheap connection handshake' against every configured backend and how per-country reachability is reported, plus the high-level response 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?

The description is structured and info-dense: a one-line purpose, a parameter breakdown, and a return summary. It loses a point for a little redundancy: 'confirms the server is up' and 'only says whether the server is up' say similar things.

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 liveness tool with one optional parameter, an output schema, and strong annotations, the description fully covers what the agent needs: purpose, parameter semantics, return contents, and how it differs from the relevant sibling. Nothing essential 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?

The schema has 0% description coverage, so the description carries the full parameter documentation burden. It fully explains check_backends: its default(false), optional nature, behavior when true, and the per-country reachability information it produces.

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 'Liveness probe' and says it 'confirms the unified register server is up,' giving a specific verb and resource. It also explicitly distinguishes itself from get_coverage by stating 'this tool only says whether the server is up,' which prevents confusion with a 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?

It names the alternative get_opcoverage for data completeness and clearly states the boundary of this tool. The optional check_backends parameter is also described with its effect, telling the agent when it is appropriate to invoke the deeper behavior.

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?

Behavioral details go well beyond the annotations: a filter unsupported in one country excludes that country and appears in 'notices' rather than being silently dropped; unreachable backends are reported via 'countries_unavailable'; and German financials must not be reported as zero due to missing DE coverage. These are exactly the hidden behaviors an agent needs to avoid incorrect 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?

The description fully front-loaded with purpose and then structured into clear labeled blocks: purpose, parameters, sort, paging, return envelope, usage warnings, and alternative tools. Although very long, every sentence covers a distinct and useful requirement for a high-complexity, multi-country search API, and there is 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?

The description is complete for a tool with this huge parameter count and cross-country behavior. It covers not only parameters but also response shape, country block behavior, error/surprise behavior, sorting defaults, and a clear reference to get_coverage for data completeness. Nothing needed to invoke the tool 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?

With 0% schema description coverage, the description fully compensates. It explains the semantics of filters (AND-combined, substring vs. meaning-based), shared vs. country-specific fields, country aliases, sort fields per country, keyset paging rules ('after' with cursors), exact_count behavior, and the country parameter. This goes far beyond the raw schema and is essential for correct calls.

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 action and resource: 'Find companies across the Austrian Firmenbuch and the German Handelsregister' and explicitly brands it as 'START HERE for any company lookup.' It also differentiates from siblings by naming get_company_details, export_companies_csv, and get_coverage for other use cases, which removes any ambiguity about the tool's role.

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 explicitly says to use this tool first for any company lookup and then directs to alternatives: get_company_details for full profiles, export_companies_csv for downloads, and get_coverage for data completeness. This gives the agent clear conditions for when to use this tool versus siblings.

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?

Beyond the annotations (readOnly, idempotent, non-destructive), the description discloses return-envelope shape, per-country matching semantics (AT matches only the primary managing director; DE matches all MDs and signatories), and the critical caveat that name-based matching with only birth-year published does not prove a single person across companies/countries. This contextual warning directly prevents agents from drawing false conclusions.

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 core purpose is front-loaded and the parameter block is organized, with every sentence earning its place. Minor deducts: it repeats defaults already present in the schema as data, and the phrase '(the notice says so)' is a slightly noisy aside in an otherwise lean definition.

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 definition is complete for a 4-parameter search tool: it covers required input, output envelope and per-card fields, per-country behavioral differences, the identity-matching hazard, and sibling-tool routing. With an output schema present, nothing an agent needs to invoke 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 description coverage is 0%, so the description carries the full burden of param semantics. It covers every one of the 4 parameters with defaults, allowed values (AT/DE/all; active/inactive/all), format (substring, case-insensitive, e.g. 'Mustermann'), and behavior implications (page_size = results per country). It exceeds what the bare JSON schema 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?

The description states a specific verb and resource: 'Find every company a person runs or represents - across BOTH registers in one call (cross-border person search)'. It names the sibling it is not ('For general company search use search_companies'), so an agent can distinguish it from search_companies 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 explicitly routes to an alternative: 'For general company search use search_companies with other filters; manager_name can be combined there too.' It also clarifies when this tool applies (person-centric cross-register search) and sets expectations with the AT vs DE matching differences, leaving no ambiguity about tool selection.

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