Server Quality Checklist

Tool Scores

• dip_search_plenarprotokollB
  3.1/5.0
  Behavior2/5

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

  No annotations are provided, so the description carries the full burden of behavioral disclosure. It only restates that full-text search is performed and matching protocols are returned, without explaining pagination behavior, result ordering, relevance ranking, or whether matches are highlighted. It adds little beyond what the name and schema already convey.

  Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

  Conciseness4/5

  Is the description appropriately sized, front-loaded, and free of redundancy?

  The description is short, front-loaded, and easy to parse in two sentences. It is slightly redundant ('full text search' appears in the schema and 'debate text' repeats the Plenarprotokoll concept), but it remains appropriately concise.

  Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

  Completeness2/5

  Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

  Given six parameters, no output schema, and no annotations, the description is too sparse. It does not explain how optional filters like date range, herausgeber, or wahlperiode affect results, nor what the returned protocol records look like. An agent could invoke it with the required query and limit but would lack context for filtering and interpreting results.

  Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

  Parameters3/5

  Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

  The schema provides descriptions for all six parameters, so baseline is 3. The description does not add meaningful parameter semantics beyond the schema; it only generally mentions full-text search. Since schema coverage is 100%, this is acceptable but not enhanced.

  Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

  Purpose5/5

  Does the description clearly state what the tool does and how it differs from similar tools?

  The description clearly identifies the action ('Search') and the specific resource ('Plenarprotokolle', parliamentary debate transcripts), and further clarifies that results are protocols containing the term in the debate text. This resource focus distinguishes it from siblings like dip_search_vorgang or the generic dip_search.

  Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

  Usage Guidelines2/5

  Does the description explain when to use this tool, when not to, or what alternatives exist?

  There is no explicit guidance about when to use this tool versus alternatives such as dip_search_vorgang, dip_search, or other search tools. No when-to-use or when-not-to-use conditions are provided; usage is only implied by the tool's name and description.

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

• eul_searchB
  3.1/5.0
  Behavior2/5

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

  With no annotations, the description carries the full burden of behavioral disclosure. It only mentions the endpoint and return fields; it does not disclose that this is a read-only SPARQL query, any rate limiting or latency behavior, how the query is matched against titles, or the meaning of language and limit in practice. It is not misleading, but it is notably under-disclosed.

  Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

  Conciseness5/5

  Is the description appropriately sized, front-loaded, and free of redundancy?

  The description is a single tightly written sentence, front-loaded with 'Search EU legislation'. It conveys the verb, resource, technical endpoint, and return values without any filler or redundancy.

  Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

  Completeness3/5

  Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

  The schema is fully described, making invocation possible. However, there is no output schema and no annotations, and the description does not explain how the returned CELEX numbers might be used with eul_get_document or how to choose among the various resource types. Given the complexity of the EUR-Lex domain, some additional context would be valuable.

  Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

  Parameters3/5

  Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

  Schema description coverage is 100%, so the parameters already carry descriptions for query, resource_type, language, and limit. The description itself does not add parameter-level detail beyond what the schema provides, so the baseline of 3 applies.

  Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

  Purpose4/5

  Does the description clearly state what the tool does and how it differs from similar tools?

  The description clearly states a specific action ('Search'), resource ('EU legislation'), endpoint ('EUR-Lex SPARQL'), and output ('CELEX numbers, titles, and dates'). It is easy to distinguish from the sibling eul_get_document by the search verb, though it does not explicitly name or contrast that sibling. It also omits 'decision' from the enumerated types even though the schema includes it.

  Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

  Usage Guidelines2/5

  Does the description explain when to use this tool, when not to, or what alternatives exist?

  No guidance is provided on when to use this tool versus alternatives such as eul_get_document or the other jurisdiction-specific search tools. The description implies it is for searching EU law but does not state exclusions, prerequisites, or how to route to a subsequent document-fetching tool.

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

• rii_searchA
  3.9/5.0
  Behavior4/5

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

  With no annotations provided, the description carries the disclosure burden, and it does say the tool 'Returns list of decisions with metadata and doc IDs for retrieval,' setting clear return expectations. It also clarifies the default source and which jurisdictions each source covers. It does not explicitly call out read-only semantics, but 'Search' plus a return list makes the non-destructive nature reasonably clear.

  Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

  Conciseness4/5

  Is the description appropriately sized, front-loaded, and free of redundancy?

  The description is four dense sentences with the purpose front-loaded, and each sentence contributes either source coverage or return behavior. The long enumeration of state source codes is somewhat heavy but necessary for source selection.

  Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

  Completeness4/5

  Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

  The description plus the fully documented schema gives an agent the source model, defaults, paging caveats, and return type (list with metadata and doc IDs). It lacks a full output field list, though no output schema exists, and it does not explicitly navigate the sibling tool landscape.

  Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

  Parameters3/5

  Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

  Schema description coverage is 100%, so the input schema already documents all seven parameters with defaults, constraints, and usage notes. The tool description adds little parameter-specific meaning beyond what the schema provides, which is acceptable under the baseline.

  Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

  Purpose4/5

  Does the description clearly state what the tool does and how it differs from similar tools?

  The description states a specific verb ('Search'), a clear resource ('court decisions'), and enumerates the covered jurisdictions and portals, so an agent immediately knows this is the German court-decision search tool. It stops short of explicitly naming sibling search tools such as ris_search or eul_search, but the resource specification is enough to distinguish it from rii_get_decision.

  Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

  Usage Guidelines4/5

  Does the description explain when to use this tool, when not to, or what alternatives exist?

  The description provides clear usage context: the default source is BUND federal courts, state source codes are enumerated, and the source parameter notes that ALL is the right choice for a topic survey because state courts are not covered by BUND. It does not explicitly state when not to use this tool versus sibling search tools, so full exclusion guidance is missing.

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

• icu_searchA
  4/5.0
  Behavior4/5

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

  With no annotations present, the description carries the full burden of explaining behavior. It clearly indicates the search scope, the information source (InfoCuria), and the exact kind of payload returned: case numbers, ECLI, dates, and document IDs. It does not mention pagination, ordering, or rate limits, but for a metadata-search tool the core behavior is well disclosed.

  Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

  Conciseness5/5

  Is the description appropriately sized, front-loaded, and free of redundancy?

  The description is a single sentence that front-loads the tool's purpose and then states the return shape. Every phrase earns its place with no repetition or filler.

  Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

  Completeness4/5

  Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

  The description is complete for a straightforward metadata search: it names the source, the resource type, and the fields returned, and it signals that IDs are for later retrieval. There is no output schema, so explaining the returned fields in prose is valuable. Minor gaps like sort order or pagination behavior are not critical for basic invocation.

  Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

  Parameters3/5

  Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

  Schema description coverage is 100%, and the schema already defines query, language, and limit with examples and constraints. The tool description adds no parameter-specific meaning beyond what the schema provides, so the baseline of 3 is appropriate.

  Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

  Purpose5/5

  Does the description clearly state what the tool does and how it differs from similar tools?

  The description states a specific verb ('Search') and resource ('decisions and opinions of the Court of Justice of the European Union (CJEU) via InfoCuria'). It distinguishes this tool from siblings like icu_get_document and other legal search tools by jurisdiction and source. An agent can tell exactly what domain and operation this tool covers.

  Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

  Usage Guidelines3/5

  Does the description explain when to use this tool, when not to, or what alternatives exist?

  The phrase 'for retrieval' implies that the returned document IDs are meant to be used with a subsequent retrieval tool, likely icu_get_document. However, the description does not explicitly name alternatives or state when to prefer this over other legal search tools. Usage context is implied rather than made explicit.

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

• legis_statesA
  4.1/5.0
  Behavior3/5

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

  With no annotations, the description carries the full burden. It clearly states it lists jurisdictions and mentions backends, but does not disclose output format, whether the data is static, or any side effects (though listing implies none). The term 'backends' is ambiguous, leaving some behavioral detail unspecified.

  Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

  Conciseness5/5

  Is the description appropriately sized, front-loaded, and free of redundancy?

  The description is a single sentence with zero fluff, front-loading the primary action ('List all 17...') and immediately providing the essential detail (which jurisdictions). Every word earns its place.

  Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

  Completeness5/5

  Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

  For a parameterless utility that lists a fixed set of jurisdictions, the description is fully complete: it tells the agent exactly what the tool does and what it returns (the 17 jurisdictions with their backends). Without an output schema or nested objects, nothing more is needed for correct invocation.

  Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

  Parameters4/5

  Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

  The tool has zero parameters and the schema coverage is 100% (empty properties). The baseline for 0 parameters is 4; the description correctly adds no parameter details since none exist, so this score is appropriate.

  Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

  Purpose5/5

  Does the description clearly state what the tool does and how it differs from similar tools?

  The description 'List all 17 available German jurisdictions (BUND + 16 Bundesländer) with their backends' states a specific verb (List), a precise resource (17 jurisdictions), and a concrete detail (with backends). It clearly distinguishes itself from sibling search/get/toc tools by its unique function of enumerating jurisdictions.

  Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

  Usage Guidelines3/5

  Does the description explain when to use this tool, when not to, or what alternatives exist?

  The description implies that this tool provides the list of jurisdictions needed for other tools but does not explicitly state when to use it or compare with alternatives. While the purpose is unmistakable, there is no guidance on when one would call this versus a search tool, nor any mention of prerequisites or typical use cases.

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

• ris_getA
  4.1/5.0
  Behavior4/5

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

  With no annotations provided, the description carries the full disclosure burden. It successfully discloses that section retrieval is token-preserving, save_path writes to disk, and save_path returns metadata only instead of content. It does not address authentication, errors, or rate limits, but the main behavioral side effects of the tool are surfaced.

  Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

  Conciseness5/5

  Is the description appropriately sized, front-loaded, and free of redundancy?

  The description is two sentences with no filler. The core retrieval purpose is front-loaded, and the remaining content packs parameter routing, mode behavior, and output implications into a tight, scannable structure.

  Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

  Completeness4/5

  Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

  The tool has no output schema and no annotations, yet the description covers the main invocation modes, output format, and side effects, so an agent can reasonably select and call it. Some gaps remain around error conditions and output details when no save_path is given, but they are not severe enough to make the definition inadequate.

  Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

  Parameters4/5

  Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

  Schema coverage is 100%, so the baseline is 3, but the description adds meaningful semantic relationships: content_url is preferred over id, applikation is conditionally required with id, section is token-preserving, and save_path changes the return behavior. This goes beyond what the property descriptions alone provide.

  Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

  Purpose4/5

  Does the description clearly state what the tool does and how it differs from similar tools?

  The description states a specific verb and resource: 'Retrieve a RIS document as Markdown.' It is clearly scoped to full documents and partial sections, and it contrasts with the broader sibling set by focusing on RIS document retrieval. It does not explicitly name or differentiate sibling tools like ris_get_norm or ris_toc, so it misses the top score.

  Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

  Usage Guidelines4/5

  Does the description explain when to use this tool, when not to, or what alternatives exist?

  The description gives strong internal guidance: prefer content_url from ris_search, use id only with applikation, use section for partial retrieval, and use save_path to write to disk while returning metadata only. It clearly explains when to use each parameter mode, but it does not state when to prefer this tool over sibling alternatives such as ris_get_norm.

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

• rii_get_decisionA
  4.2/5.0
  Behavior4/5

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

  With no annotations, the description carries the behavioral disclosure burden and does disclose the response form: 'Returns decision in Markdown format with metadata (court, date, file number, ECLI).' It also communicates the source-specific ID format. It does not cover error behavior or the save_path mode, but the retrieval action and return format are sufficiently transparent.

  Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

  Conciseness5/5

  Is the description appropriately sized, front-loaded, and free of redundancy?

  The description is two short sentences and front-loads the main action and output before adding the source-specific note. Every clause earns its place and no information is repeated from the schema.

  Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

  Completeness4/5

  Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

  For a 5-parameter tool with no annotations and no output schema, the description covers the essential invocation path and the source parameter nuance. The remaining parameters are fully documented in the input schema, so the description is largely complete; only error and edge-case behavior is omitted.

  Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

  Parameters4/5

  Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

  Schema coverage is 100%, so the baseline is 3, but the description adds a real semantic mapping beyond the schema: BY-source IDs come from gesetze-bayern.de and use the Y-300-Z-... format. This external context helps an agent construct correct IDs. Other parameters do not need further elaboration because the schema already documents them.

  Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

  Purpose5/5

  Does the description clearly state what the tool does and how it differs from similar tools?

  The description opens with a specific verb, resource, and lookup key: 'Retrieve full text of a court decision by doc ID.' It clearly distinguishes this from sibling search tools by framing it as a retrieval action keyed on an ID, and it states the expected output format.

  Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

  Usage Guidelines3/5

  Does the description explain when to use this tool, when not to, or what alternatives exist?

  The only explicit usage guidance is 'Use source "BY" for IDs from gesetze-bayern.de (format: Y-300-Z-...),' which helps select a parameter value but not choose this tool over alternatives. It implies the tool is used when a doc ID already exists, but it never states that rii_search should be used first or when not to use this tool.

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

• ris_get_normA
  4.2/5.0
  Behavior3/5

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

  With no annotations provided, the description carries the behavioral disclosure burden. It discloses the output format (Markdown), the consolidated-law source, and jurisdiction switching behavior. However, it omits any mention of the save_path side effect and does not address potential errors or output behavior beyond format, leaving notable behavioral gaps.

  Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

  Conciseness5/5

  Is the description appropriately sized, front-loaded, and free of redundancy?

  The description is a single well-structured sentence that front-loads the main action, includes a concrete example, and adds a concise contrast with whole-statute retrieval. Every phrase earns its place without redundancy.

  Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

  Completeness4/5

  Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

  For a relatively simple retrieval tool with fully documented schema parameters, the description covers the core purpose, the Markdown output format, jurisdiction handling, and a concrete example. It is slightly incomplete because it never mentions the optional save_path behavior or explicitly ties the tool to sibling tools, but overall it gives an agent enough to invoke it correctly in common cases.

  Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

  Parameters4/5

  Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

  Schema coverage is 100%, so the baseline is 3. The description adds value by giving a concrete example (law="ABGB" paragraph="1295"), clarifying how application selects federal vs state law, and signaling that bundesland must be set in the landesrecht case. This goes beyond the schema's field descriptions.

  Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

  Purpose5/5

  Does the description clearly state what the tool does and how it differs from similar tools?

  Description opens with a specific verb and resource: "Retrieve a single paragraph (§) of an Austrian consolidated law as Markdown." It further distinguishes itself by contrasting with "a whole statute," which differentiates it from siblings like ris_get, and provides a concrete law/paragraph example.

  Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

  Usage Guidelines4/5

  Does the description explain when to use this tool, when not to, or what alternatives exist?

  The description clearly communicates the intended use case: the "surgical, token-preserving way to read ONE § instead of a whole statute." It also gives selection context for application="bundesrecht" vs "landesrecht" and notes that bundesland is needed for state law. However, it does not explicitly name sibling tools or say when not to use them, so it falls just short of full alternative routing.

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

• arxiv_searchA
  4.3/5.0
  Behavior4/5

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

  No annotations are provided, so the description carries the behavioral burden. It clearly discloses that the tool returns metadata and links, and that full text is not returned but belongs to arxiv_get. It does not mention error handling or rate limits, but for a read/search tool the key behavioral boundary is well communicated.

  Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

  Conciseness5/5

  Is the description appropriately sized, front-loaded, and free of redundancy?

  Two tight, front-loaded sentences: the first states the action, target, and search dimensions; the second lists return fields and routes full-text retrieval to arxiv_get. 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.

  Completeness5/5

  Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

  Although there is no output schema, the description enumerates the important return fields and links. Required parameters and pagination are already documented in the input schema, and the arxiv_get handoff completes the workflow. An agent has enough context to select and invoke this tool correctly.

  Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

  Parameters3/5

  Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

  Schema description coverage is 100%, so the baseline is 3. The description's mention of keywords, author, and category adds conceptual framing, but the schema already documents query prefixes, limit defaults, start offset, and sort options. The description does not add significant value beyond the structured schema.

  Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

  Purpose5/5

  Does the description clearly state what the tool does and how it differs from similar tools?

  The description uses a specific verb ('Search') and a clear resource ('arXiv preprints') and further specifies search dimensions: keywords, author, or category. It also states the output fields, making it immediately distinguishable from arxiv_get, which is called out for full-text retrieval.

  Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

  Usage Guidelines4/5

  Does the description explain when to use this tool, when not to, or what alternatives exist?

  The description explicitly routes full-text retrieval to arxiv_get, which clarifies when arxiv_search should be used versus its sibling arxiv_get. It does not provide explicit exclusions or compare with other sibling search tools, but the workflow guidance is clear enough for an agent.

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

• dip_getA
  4.4/5.0
  Behavior4/5

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

  With no annotations, the description carries the behavioral disclosure burden and does reasonably well: it states that full text is returned, that output includes Gesetzesbegründung, and that save_path triggers export behavior only when the user wants a file. It could state more explicitly that a file is written to save_path, but the semantics are conveyed.

  Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

  Conciseness5/5

  Is the description appropriately sized, front-loaded, and free of redundancy?

  The description is four short sentences with no filler. The core action and required identifier come first, followed by the output guarantee and then the two optional-parameter clarifications.

  Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

  Completeness4/5

  Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

  Given there is no output schema, the description adequately explains what is returned (extracted text including Gesetzesbegründung). It covers the required parameter, the optional section param, and the export-only save_path. A small gap is the lack of an explicit note about what happens when the document is not found, but this is not critical for selection and invocation.

  Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

  Parameters4/5

  Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

  The input schema already documents all three parameters (100% coverage), so the baseline is 3. The description adds value beyond the schema by clarifying that section is for partial extraction and that save_path is for file export, not normal return behavior.

  Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

  Purpose5/5

  Does the description clearly state what the tool does and how it differs from similar tools?

  The description contains a specific verb and resource: "Retrieve full text of a Bundestagsdrucksache by Dokumentnummer." It also gives a concrete example ("19/27426") and clearly differentiates this from the sibling search tools by requiring an exact document number.

  Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

  Usage Guidelines4/5

  Does the description explain when to use this tool, when not to, or what alternatives exist?

  The description gives clear usage direction for optional parameters: "Use `section` for partial content" and "`save_path` is for export only." It does not explicitly tell the agent to use the sibling dip_search tools when no Dokumentnummer is known, but for this tool's narrow retrieval purpose the guidance is otherwise clear.

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

• dip_search_vorgangA
  4.4/5.0
  Behavior4/5

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

  No annotations are provided, so the description carries the behavioral burden. It discloses the core matching behavior (literal substring on title, not keyword AND/OR) and what the response contains (status, linked Drucksachen-Nummern). It could mention more edge behavior, but it covers the most important traits.

  Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

  Conciseness5/5

  Is the description appropriately sized, front-loaded, and free of redundancy?

  Three sentences, each earning its place: purpose, return value, and usage guidance. The most important scoping detail (literal substring, not keyword search) is front-loaded and clearly stated.

  Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

  Completeness4/5

  Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

  For a search tool with 6 parameters and no output schema, the description gives enough orientation: what is searched, what is returned, and how to phrase queries. The schema covers parameter details. Minor gap: it does not clarify that vorgangstyp can target non-Gesetzgebung Vorgang types, but this is not blocking.

  Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

  Parameters3/5

  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 all parameters well. The description reinforces the query parameter's substring semantics but does not add meaning beyond what the schema already states.

  Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

  Purpose5/5

  Does the description clearly state what the tool does and how it differs from similar tools?

  The description clearly states the tool searches legislative processes (Vorgänge) in DIP and returns Gesetzgebungsvorgänge with status and linked Drucksachen-Nummern. It also differentiates itself from sibling dip_search by explicitly describing the literal-substring matching behavior.

  Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

  Usage Guidelines5/5

  Does the description explain when to use this tool, when not to, or what alternatives exist?

  It gives explicit when-to-use context (tracking a law or finding related documents) and an explicit when-not-to-use signal: this is NOT a keyword AND/OR search, and dip_search is named as the alternative. It also advises preferring a single distinctive word over a natural-language phrase.

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

• eul_get_documentA
  4.4/5.0
  Behavior4/5

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

  With no annotations, the description carries the disclosure burden. It discloses that the return format is Markdown, that section extracts a portion with accepted patterns, and that save_path is an export-only side effect. It does not discuss errors, limits, or file overwrite behavior, but core behavior is transparent.

  Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

  Conciseness5/5

  Is the description appropriately sized, front-loaded, and free of redundancy?

  Three sentences front-load the purpose, then cover partial extraction and export behavior with no filler. Each sentence earns its place and examples are compact.

  Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

  Completeness4/5

  Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

  For a get-by-identifier tool with four parameters and no output schema, the description covers the essential invocation details: identifier format, return format, section behavior, and save_path semantics. Slight gap: no mention of what happens on invalid CELEX numbers or very large documents, but this is not critical for correct selection.

  Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

  Parameters4/5

  Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

  Schema coverage is 100%, so baseline is 3. The description adds value by giving concrete accepted section formats ('Art. 5', 'Artikel 5', 'lines:100-200') and clarifying save_path is for export only, going beyond the schema's generic descriptions.

  Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

  Purpose5/5

  Does the description clearly state what the tool does and how it differs from similar tools?

  Description opens with a specific verb and resource: 'Retrieve EU legislation from EUR-Lex by CELEX number', with concrete examples (GDPR, InfoSoc). This clearly distinguishes a get-by-CELEX operation from search-oriented siblings such as eul_search.

  Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

  Usage Guidelines4/5

  Does the description explain when to use this tool, when not to, or what alternatives exist?

  The description provides clear context for invocation: use a CELEX number, use section for partial content, and use save_path only for file export. It does not explicitly name alternatives or say when not to use this tool, but the conditions are strongly implied.

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

• legis_getA
  4.4/5.0
  Behavior4/5

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

  With no annotations provided, the description carries the full behavioral burden, and it handles this well by disclosing automatic prefix stripping, equivalence of different section formats, and the non-obvious limitation that some reissued laws use a different URL slug. It does not explicitly describe return or save behavior, which is a minor gap.

  Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

  Conciseness4/5

  Is the description appropriately sized, front-loaded, and free of redundancy?

  The description is dense and front-loaded, with the core purpose stated first and each subsequent sentence contributing useful details or examples. It is longer than a minimal description, but the complexity of the id format justifies the length; no sentence feels like filler.

  Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

  Completeness4/5

  Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

  The description is nearly complete for this tool's main difficulty—constructing and interpreting the id across BUND and Länder jurisdictions. It also covers edge cases like prefix normalization and not-found fallback, but it leaves the output/save semantics implicit rather than stating what the tool returns or when save_path is necessary.

  Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

  Parameters5/5

  Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

  The description substantially enriches the id parameter beyond the schema: it explains BUND's 'law/section' anatomy, requires lowercase law abbreviations, documents equivalent prefix forms, and distinguishes Länder IDs. The state and save_path parameters are already well described in the schema, and the 100% schema coverage supports a high score.

  Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

  Purpose5/5

  Does the description clearly state what the tool does and how it differs from similar tools?

  The description opens with a specific verb and resource: 'Retrieve a specific law/norm from German federal or state legislation.' It clearly separates this point-lookup tool from sibling search/toc tools such as legis_search and legis_toc by focusing on a single known document rather than discovery or navigation.

  Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

  Usage Guidelines4/5

  Does the description explain when to use this tool, when not to, or what alternatives exist?

  The description gives clear operational guidance: for Länder, the ID must come from legis_search results, and if the lookup returns 'not found', it advises a subscription-provider fallback. It does not explicitly state 'use legis_search to discover IDs, use legis_get once you have them,' but the workflow is strongly implied.

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

• legis_tocA
  4.4/5.0
  Behavior4/5

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

  With no annotations, the description carries the transparency burden. It discloses that the result is a 'compact list' without full text, and that it is designed for efficient navigation of large laws. It does not mention error behavior or rate limits, but for a read-only retrieval tool the core behavioral traits are sufficiently conveyed.

  Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

  Conciseness5/5

  Is the description appropriately sized, front-loaded, and free of redundancy?

  Three short sentences lead with the core purpose, then the key comparison with legis_get, then the id-construction rule. Every sentence earns its place and there is no filler or repeated schema content.

  Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

  Completeness4/5

  Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

  For a tool with 5 parameters, a complete schema, and no output schema, the description covers the essential decision-making and invocation context: what it returns, when to prefer it, and how to obtain ids. It does not specify default depth behavior or differentiate from ris_toc, but those are secondary given the schema's parameter descriptions.

  Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

  Parameters4/5

  Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

  Schema description coverage is 100%, so the baseline is 3. The description adds real value beyond the schema by explaining how to construct the id: a plain law abbreviation for BUND and a legis_search result id for Länder. This is exactly the kind of contextual parameter knowledge an agent needs.

  Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

  Purpose5/5

  Does the description clearly state what the tool does and how it differs from similar tools?

  The opening phrase 'Get table of contents for a law — compact list of section numbers and headings' names a specific verb, resource, and output shape. It also differentiates itself from the sibling legis_get by calling itself 'much lighter,' so an agent can distinguish it without opening schemas.

  Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

  Usage Guidelines4/5

  Does the description explain when to use this tool, when not to, or what alternatives exist?

  The description gives clear context: use this tool for navigating large laws when a lightweight table of contents is preferable to legis_get. It also instructs that Länder ids must come from legis_search results, which is an actionable workflow hint. It does not explicitly state when to choose legis_get instead, but the lighter/heavier contrast implies it.

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

• icu_get_documentA
  4.5/5.0
  Behavior4/5

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

  With no annotations, the description carries the behavioral burden and discloses the Markdown return format including Randnummern markup, the internal CELEX conversion, partial-content extraction, and the file-writing side effect of save_path. It does not describe error behavior or file-overwrite semantics, but the main behaviors and side effects are clearly surfaced.

  Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

  Conciseness5/5

  Is the description appropriately sized, front-loaded, and free of redundancy?

  The description is compact and dense, with each sentence carrying distinct and necessary information: target and return format, identifier resolution, section usage, and save_path usage. It is front-loaded with the core purpose and contains no redundant filler.

  Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

  Completeness5/5

  Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

  The description covers all four parameters, the return format, identifier conversion behavior, partial extraction syntax, and the file-saving use case. Even without an output schema or annotations, an agent has enough context to select and invoke this tool correctly and to understand how it relates to icu_search.

  Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

  Parameters4/5

  Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

  Schema coverage is 100%, so the baseline is 3, and the description adds meaning beyond the schema: it explains why the three case_id forms are equivalent, which forms are faster to resolve, and gives concrete examples for section and save_path usage. This helps the agent choose appropriate values rather than just satisfy schema constraints.

  Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

  Purpose5/5

  Does the description clearly state what the tool does and how it differs from similar tools?

  States the specific operation — retrieve a CJEU decision or opinion from InfoCuria — and names the three accepted identifier forms. It is clearly distinct from search siblings by focusing on full-text retrieval and references icu_search's Logic Doc ID as an input source.

  Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

  Usage Guidelines4/5

  Does the description explain when to use this tool, when not to, or what alternatives exist?

  Gives explicit guidance on which identifier form to use, notes that CELEX numbers and Logic Doc IDs resolve with one request fewer, and explains when to use section and save_path. It does not explicitly contrast this tool with sibling get tools such as eul_get_document, so exclusions are mostly left to the tool name and purpose.

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

• legis_searchA
  4.6/5.0
  Behavior4/5

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

  With no annotations, the description carries the behavioral burden. It usefully discloses that results contain IDs for retrieval, that state coverage includes all 16 Bundesländer, that federal law is not searchable, and that abbreviations can outperform descriptive phrases. It does not describe response shape, pagination, or error behavior, but the core calling behavior is clear.

  Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

  Conciseness5/5

  Is the description appropriately sized, front-loaded, and free of redundancy?

  Three short sentences, each earning its place: the action, the output link to legis_get, the search tip, the geographic scope, and the critical BUND exception. No filler or repetition of schema details.

  Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

  Completeness4/5

  Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

  For a 3-parameter search tool with no output schema and no annotations, the description covers the essential operational facts: what is searched, what the results provide, scope, and the federal exception. It stops short of explaining result ordering, pagination, or empty-result behavior, but an agent can invoke the tool correctly with what is given.

  Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

  Parameters4/5

  Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

  Schema description coverage is 100%, so the baseline is 3. The description adds value beyond the schema by advising that official abbreviations like 'HKG' or 'PolG' tend to be more reliable than descriptive phrases for the query parameter. This is practical, non-obvious guidance that the schema examples only partially provide.

  Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

  Purpose5/5

  Does the description clearly state what the tool does and how it differs from similar tools?

  The description opens with a specific verb and resource: 'Search German state legislation (Landesrecht) by keyword.' It clarifies that results carry IDs for retrieval via legis_get, and it explicitly excludes BUND, making the tool's scope unambiguous and distinguishing it from related siblings.

  Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

  Usage Guidelines5/5

  Does the description explain when to use this tool, when not to, or what alternatives exist?

  The description gives an explicit when-not-to-use directive: 'BUND does not support search — use legis_get directly.' It also supplies practical guidance that official abbreviations are often more reliable and notes coverage of all 16 Bundesländer, so an agent knows both when and how to use the tool.

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

• arxiv_getA
  4.7/5.0
  Behavior5/5

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

  With no annotations, the description carries the full burden, and it does so well: it discloses the default output (metadata + abstract), the conditional full-text behavior triggered by section or save_path, the ~2024+ HTML availability constraint, and the fallback for older papers. This is unusually transparent about mode-dependent behavior.

  Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

  Conciseness5/5

  Is the description appropriately sized, front-loaded, and free of redundancy?

  Three sentences with no filler: purpose is front-loaded, the default behavior is stated, and the conditional/fallback behavior follows logically. Every sentence contributes necessary information.

  Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

  Completeness5/5

  Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

  For a simple three-parameter fetch tool with no output schema, the description is complete: it covers the main use, optional parameter effects, an important availability boundary, and the fallback result. An agent has enough to invoke it correctly and predict what will happen.

  Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

  Parameters4/5

  Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

  Schema coverage is 100% and the schema already documents id, section, and save_path well. The description adds value by explaining the default when no optional parameters are provided and by tying section/save_path to full-text HTML fetching, including the availability caveat.

  Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

  Purpose5/5

  Does the description clearly state what the tool does and how it differs from similar tools?

  The description opens with a specific verb and resource: 'Retrieve an arXiv paper by ID,' and gives a concrete ID example. This clearly distinguishes the tool from arxiv_search, which would be used to discover papers rather than fetch a known one.

  Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

  Usage Guidelines4/5

  Does the description explain when to use this tool, when not to, or what alternatives exist?

  The description establishes that this tool is for known arXiv IDs ('by ID'), which gives clear context for when to invoke it. It does not explicitly name arxiv_search as the alternative for finding papers or state when not to use this tool, so it stops short of full exclusion guidance.

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

• dip_searchA
  4.9/5.0
  Behavior5/5

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

  With no annotations, the description carries the full behavioral burden, and it delivers: it discloses the literal-substring matching rule, the 'NOT keyword AND/OR' semantics, a concrete failure example, and the reverse-order/word-ending pitfall. It also states the return metadata fields. This far exceeds typical 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.

  Conciseness5/5

  Is the description appropriately sized, front-loaded, and free of redundancy?

  Every sentence earns its place: purpose, core matching constraint, illustrative example, search recommendation, return payload, and pointer to dip_get. The longer-than-usual length is justified by the unusual search semantics that must be communicated to avoid failed queries.

  Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

  Completeness5/5

  Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

  For a search tool with no output schema, the description is complete: it explains what is searched, how the search behaves, what results look like, and how to get full documents. Filter parameters like type, date, and wahlperiode are adequately covered by the schema.

  Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

  Parameters4/5

  Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

  Schema coverage is 100%, so the baseline is 3. The description adds strong value for the query parameter by explaining the required verbatim substring behavior and recommending single distinctive words, going well beyond the schema's generic wording. Other parameters are already fully documented in the schema.

  Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

  Purpose5/5

  Does the description clearly state what the tool does and how it differs from similar tools?

  The description states a specific verb and resource: 'Search Bundestagsdrucksachen (parliamentary documents) via DIP API.' It clearly distinguishes from siblings by document type (Drucksachen vs Vorgang/Plenarprotokoll) and from dip_get by noting the difference between search and full-text retrieval.

  Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

  Usage Guidelines5/5

  Does the description explain when to use this tool, when not to, or what alternatives exist?

  It gives explicit usage guidance: match titles as literal substrings, prefer a single distinctive word, avoid natural-language phrases, and use dip_get instead when full text is needed. This tells the agent both how to use this tool and when to delegate to an alternative.

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

• ris_tocA
  4.9/5.0
  Behavior5/5

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

  There are no annotations, so the description carries the full burden. It clearly states what the tool returns (TOC with §§ and headings), what inputs affect behavior (full title vs abbreviation, application scope), and implies a network fetch to the RIS service. It does not hide side effects or require inferred prerequisites, making it behaviorally transparent for an agent.

  Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

  Conciseness5/5

  Is the description appropriately sized, front-loaded, and free of redundancy?

  Three sentences with high information density. Every sentence adds distinct value: purpose and follow-up, practical abbreviation advice, and legal-scope parameters. There is no fluff or repetition of schema details.

  Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

  Completeness5/5

  Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

  The tool has no output schema and no annotations, so the description is the only source of behavioral and usage context. It covers the purpose, the expected content (TOC with §§ and headings), the follow-up tool, the two application scopes, and the parameter dependency between application and bundesland. This is sufficient for an agent to invoke it correctly.

  Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

  Parameters4/5

  Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

  The schema already has 100% coverage, so the baseline is 3. The description adds meaningful usage context: it explicitly mentions using the full title when an abbreviation fails, which supplements the schema's 'Law title or abbreviation' example. It also clarifies that bundesland is needed for landesrecht. Only minor extra value beyond schema, hence 4.

  Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

  Purpose5/5

  Does the description clearly state what the tool does and how it differs from similar tools?

  The description explicitly states the tool retrieves the table of contents of an Austrian consolidated law, listing its §§ with headings, and names the follow-up tool ris_get_norm. It differentiates from siblings like ris_get and ris_get_norm by specifying the TOC retrieval purpose.

  Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

  Usage Guidelines5/5

  Does the description explain when to use this tool, when not to, or what alternatives exist?

  The description gives concrete when-to-use guidance: use it to get a TOC before reading a norm with ris_get_norm, and advises using full titles if abbreviations fail. It also explains that application='bundesrecht' or 'landesrecht' with bundesland, which provides clear selection criteria.

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

• ris_searchA
  5/5.0
  Behavior5/5

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

  Because no annotations are provided, the description carries the full behavioral disclosure burden. It reveals that results may be consolidated law or authentic publications identified by `applikation`, that bundesland restricts to LrKons, and that judikatur returns Rechtssätze that list the full Entscheidungstext. The Austrian-vs-German jurisdiction warning is useful behavioral context.

  Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

  Conciseness5/5

  Is the description appropriately sized, front-loaded, and free of redundancy?

  The description is dense but every sentence earns its place: it starts with the resource, moves through application-specific behavior, and closes with cross-tool routing. It does not restate schema details or include filler.

  Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

  Completeness5/5

  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's explanation of result types, Rechtssätze, and the full Entscheidungstext is critical and present. It covers all three application modes, filters, sorting, and the follow-up tool (ris_get), so an agent has enough context to invoke it correctly.

  Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

  Parameters5/5

  Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

  Schema coverage is 100%, so the baseline is 3, but this description adds substantive meaning beyond the schema: bundesland filters to consolidated LrKons, court values map to specific courts (Justiz = OGH/OLG/LG, etc.), and sort='date' means latest decisions. This helps agents choose parameter values correctly, not just understand their names.

  Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

  Purpose5/5

  Does the description clearly state what the tool does and how it differs from similar tools?

  States a specific verb ('Search') and a specific resource: the Austrian Rechtsinformationssystem des Bundes (RIS). It also differentiates from sibling tools by explicitly routing German case law to rii_* and German legislation to legis_*, and by pointing to ris_get for fetching full decision texts.

  Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

  Usage Guidelines5/5

  Does the description explain when to use this tool, when not to, or what alternatives exist?

  Provides explicit usage guidance per application value: bundesrecht/landesrecht for broad law collections, judikatur for case law with court selection, and bundesland for consolidated state law. It also gives exclusions ('For GERMAN case law use rii_*, for German legislation use legis_*') and tells agents when to use sort='date'.

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