Server Quality Checklist

Tool Scores

• list_amendmentsA
  3.8/5.0
  Behavior3/5

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

  No annotations are present, so the description carries the behavioral disclosure burden. It states the return nature (dates) but says nothing about read-only behavior, authorization requirements, pagination, or side effects. For a listing tool this is a moderate gap, not a critical one.

  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 short sentences with zero waste. The action and result are front-loaded, and every sentence contributes meaning.

  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 simple list tool with one required parameter and no output schema, the description covers action, resource, and result. It lacks detail on output format and how language/since affect results, but those are documented in the schema, so the definition is largely sufficient.

  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?

  Input schema already describes all three parameters with 100% coverage, so the baseline is 3. The description adds no parameter-specific semantics beyond the schema, though the phrase 'consolidated version dates' loosely contextualizes rs_number and since.

  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 ('List') and resource ('consolidation version dates for a Swiss federal act') and clarifies the output ('the dates each consolidated version took effect'). This clearly distinguishes it from siblings like search_by_title or get_article.

  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?

  No explicit guidance on when to use this tool versus alternatives, and no exclusions or conditions are provided. The intended use is only implied by the description's statement of what it returns.

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

• search_by_titleA
  4.2/5.0
  Behavior4/5

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

  No annotations are provided, so the description carries the full burden. It discloses important behaviors beyond the bare operation: it matches titles only, excludes article content, and filters to acts currently in force. It does not describe result format or pagination, but for a simple search tool the core behavioral traits are well covered.

  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 three sentences with no fluff. It front-loads the action and domain, then adds the key differentiator and result filtering. Every sentence earns its place.

  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 no output schema and no annotations, the description covers the main facts an agent needs: what is searched, why to use it, what is excluded, and the in-force filter. It could mention result fields or language behavior in more detail, but the tool is simple and the description is largely sufficient.

  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 explains both query and language parameters, including an example and the default language. The description adds no parameter-level semantics beyond what the schema provides, so the baseline 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'), a specific resource ('Swiss federal legislation titles in the Classified Compilation (RS/SR) on Fedlex'), and a clear intended outcome ('find the RS number of a law'). It also distinguishes itself from content search by saying it searches titles only, which differentiates it from siblings like get_article.

  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 says when to use it: when you know a law's name but not its RS number. It also states what it does not do ('Searches titles only, not article content') and that it returns only in-force acts, which are useful exclusions. It does not explicitly name alternative sibling tools, so it stops short of a perfect 5.

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

• get_law_textA
  4.3/5.0
  Behavior4/5

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

  With no annotations provided, the description carries the full burden and does well: it clarifies that the tool fetches official consolidated text, can target a full act or a section, and instructs the agent to 'locate relevant provisions in the returned text.' It does not describe error cases or rate limits, but this is a read-only retrieval tool and the core behavior is clearly disclosed.

  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 appropriately sized and front-loaded with the core purpose. It contains a small amount of redundancy—'Fetch the full act or a specific section' partially repeats the first sentence and the schema—but each sentence still contributes useful usage or workflow context, so it earns a score above baseline.

  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 four parameters, a full schema, and no output schema, the description provides enough context to call the tool correctly: source, primary use case, section behavior, and how to process the returned text. It does not mention fallback to search_by_title when rs_number is unknown, but the schema and sibling list make this recoverable.

  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 schema already explains rs_number, section, language, and page with examples. The description adds minor reinforcement by mentioning 'specific title/chapter' and 'full act or a specific section,' but it does not materially extend the parameter meaning beyond 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 uses a specific verb-resource pair: 'Retrieve the official consolidated text of a Swiss federal act' and names the exact source, Fedlex. It further distinguishes this tool from siblings by declaring itself the 'PRIMARY tool for answering Swiss law questions' and explicitly prefers it over get_article unless an exact article number is known.

  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 direct when-to-use guidance: 'always start here' for Swiss law questions, and states the condition for choosing get_article instead ('unless you already know the exact article number'). This is explicit enough for an agent to route correctly without opening other tool schemas.

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

• get_articleA
  4.4/5.0
  Behavior3/5

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

  No annotations are provided, so the description carries the full burden. It discloses that the tool returns a single article and that repeated calls are inappropriate for searching. However, it does not describe the return format, error behavior for invalid article numbers, or versioning behavior beyond the date parameter's schema description. The description provides moderate behavioral context but leaves room for more.

  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 sentences, both earning their place. The first states the tool's purpose and the key precondition (exact article number), and the second provides critical usage prohibition and routing to the alternative. No fluff, perfectly front-loaded.

  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 simple single-article retrieval tool with 100% schema coverage, the description covers the essential context: exact-number precondition, the search disincentive, and the alternative routing. The only gaps are the absence of any return-format or error-handling description, but for such a focused tool with a well-documented schema, this is a minor omission.

  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 all four parameters are documented in the schema itself. While the description doesn't add parameter-level detail beyond the schema, it provides essential semantic context: that 'article' must be an exact number from a cross-reference, which clarifies the precision requirement. This adds value beyond the schema's generic description of article as just 'Article number'.

  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 retrieves a single article when the exact article number is known, using a specific verb ('Retrieve') and resource. It also differentiates from the sibling tool get_law_text by explicitly stating what it is NOT for, which makes its purpose unambiguous.

  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 explicit when-to-use guidance ('when you already know the EXACT article number'), an explicit when-not-to-use instruction ('Do NOT call this tool repeatedly to search for provisions'), and names the alternative tool (get_law_text) with guidance on how to use it instead. This is exemplary usage guidance.

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