Server Quality Checklist

Tool Scores

• cerca_normativaA
  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 explanatory burden. It discloses the BM25 ranking behavior, the result fields, the effect of solo_vigenti, and the instruction to cite act and article. It conveys that this is a read/search operation, and there are no hidden destructive side effects.

  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 every sentence earns its place: the search behavior, the mandatory usage instruction, the output citation rule, and parameter semantics are all included without waste. The imperative 'USA SEMPRE' is intentionally attention-grabbing and reinforces the priority of this tool.

  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 invocation: it explains purpose, when to use, all parameters, and the structure of results. It could be slightly richer by explaining how it relates to sibling tools or what to do when the ordinary law details are not sufficient, but nothing essential is missing for calling the tool 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?

  The schema has 0% description coverage, but the description compensates fully by defining every parameter: query as free text, solo_vigenti as excluding repealed acts, and limit as the maximum number of extracts with a default of 8. This adds substantial meaning beyond the bare schema types and titles.

  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 the tool searches Italian legislation and returns the most relevant normative extracts using BM25 ranking, which is specific and action-oriented. It does not explicitly mention sibling tools, but the search scope is clear enough for an agent to distinguish it from leggi_atto and info_corpus.

  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?

  It gives an explicit usage directive: always use this tool before answering Italian law questions and do not answer from memory. However, it does not state when not to use it or mention alternatives, so the guidance is strong on when but not on exclusions.

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

• info_corpusA
  4.5/5.0
  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 of behavioral disclosure. It explains what informational data the tool returns (act count, chunk count, commit, update date) and also instructs the agent to cite the disclaimer. This is sufficient for a read-only status tool, though it does not explicitly state that no mutations occur.

  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 redundancy: the first sentence front-loads the tool's purpose and output data, and the second explains the intended usage context. Every clause 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 simple informational tool with no parameters and no output schema, the description is complete: it names the output fields, gives an explicit use case, and adds the disclaimer instruction. An agent has all it needs to decide when to call this tool and how to present the results.

  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 full schema coverage, so the description does not need to clarify any inputs. According to the baseline for parameterless tools, a score of 4 is appropriate; the description adds no irrelevant parameter information.

  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 tool as providing status and freshness of the indexed corpus, including specific outputs: number of acts, number of chunks, commit, and last update date. This domain is distinct from siblings cerca_normativa (search) and leggi_atto (read), so an agent can easily tell it apart.

  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 states when to use the tool: to tell the user how up-to-date and broad the normative base supporting the answer is, and to cite the disclaimer. It lacks explicit 'when not to use' guidance, but the use case is clearly described and the tool's scope is obvious from the context.

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

• leggi_attoA
  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 burden and does well: it discloses that the tool is a read operation ('Legge'), that it sources from an index, that it can return a whole act or a single article, and that urn is preferred over path. It stops short of explaining error behavior or response format, which is a minor gap for a retrieval tool.

  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 dense sentences with no filler. The main purpose is front-loaded, and every sentence adds useful information: the object being read, the identification methods, the article filter, and the recommended workflow.

  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 read tool with no output schema and no annotations, the description is largely complete: it explains the selector parameters and the workflow with the key sibling. It could add what happens when no matching act is found or what the returned text looks like, but the core calling context is well covered.

  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 0%, so the description must compensate, and it does: it defines urn as the preferred identifier, path as an alternative, and articolo as an optional filter that restricts output to a single article. It adds semantics that the bare schema does not provide, though it leaves details like value formats implied.

  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: 'Legge il testo integrale di un atto, o di un suo singolo articolo, dall'indice.' It makes clear this tool reads full legal text, and it distinguishes itself from cerca_normativa by defining the workflow: cerca_normativa finds the act, this tool reads it.

  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 explicitly states when to use the tool: 'Usalo per leggere il testo completo dopo che cerca_normativa ha individuato l'atto rilevante.' It also frames urn as the preferred identifier because it is returned by cerca_normativa, giving concrete routing guidance.

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