Server Quality Checklist

Tool Scores

• list_activitiesB
  3.4/5.0
  Behavior2/5

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

  Aucune annotation n'est fournie, donc la description doit assumer seule la transparence comportementale. Elle précise que les valeurs sont compatibles avec search_treks et proviennent de l'instance configurée, mais elle ne dit rien sur l'effet de force_refresh, d'éventuels caches, des autorisations ou des limites.

  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?

  La description est concise, en deux phrases, avec des exemples utiles et une information principale en tête. Aucun mot superflu.

  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?

  La présence d'un schéma de sortie et l'indication d'usage avec search_treks fournissent un contexte utile. Cependant, le seul paramètre d'entrée force_refresh reste non expliqué, ce qui constitue une lacune notable pour une description qui se veut complète.

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

  Parameters1/5

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

  Le paramètre force_refresh n'est absolument pas mentionné dans la description, alors que la couverture du schéma est de 0% et que le nom seul n'apporte pas de sens. La description ne compense pas ce manque, ce qui laisse l'utilisateur sans information sur le comportement du paramètre.

  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?

  Le verbe 'Liste' et le complément 'types d'activité (pratiques) disponibles' identifient clairement l'objet et le périmètre. Les exemples et le lien explicite vers search_treks distinguent bien l'outil de list_labels et search_treks.

  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?

  La description indique précisément un cas d'usage concret : les noms retournés peuvent être injectés tels quels dans practice_names de search_treks. En revanche, elle ne mentionne pas de cas où l'outil ne doit pas être utilisé, ni d'alternative explicite.

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

• list_labelsA
  3.6/5.0
  Behavior3/5

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

  No annotations are provided, so the description must carry the behavioral burden. It clearly indicates a read/list operation and adds context about compatibility with search_treks. However, it does not explain the behavior of the force_refresh parameter, caching, or the return format, leaving meaningful 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 two tight sentences: the first front-loads the purpose with examples, and the second gives a concrete usage tip. Every sentence earns its place and there is no redundant filler.

  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 tool is simple with an output schema, and the description covers its core purpose and integration with search_treks. However, the undocumented force_refresh parameter and lack of explicit differentiation from list_activities make the description not fully complete for an agent selecting and invoking the tool.

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

  Parameters1/5

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

  The only parameter, force_refresh, has no schema description and is not mentioned in the tool description at all. With 0% schema description coverage, the description provides no compensatory meaning for this parameter.

  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 ('Liste') with a clear resource ('labels de réglementation disponibles sur l'instance GeoTrek configurée') and includes concrete examples. It is clearly distinguished from the sibling tool list_activities (labels vs activities) and explicitly relates to search_treks via the label_names parameter.

  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 explains that returned names can be used directly in search_treks' label_names parameter, providing concrete usage context. It does not explicitly state when not to use this tool or contrast it with list_activities, so it stops short of full guidance.

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

• search_treksA
  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 full burden and does so well: it discloses filter behavior, units, default radius, and the use of Nominatim for geocoding. It omits return format and error behavior, but an output schema exists to cover some of that.

  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 a single organized paragraph, front-loaded with the purpose and then a structured enumeration of filters. It is efficient with no wasted words, though bullet points could improve scannability.

  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?

  For a tool with 12 parameters and no annotations, the description covers most filters but leaves `limit` and `query_text` unexplained, and lacks details on search result ordering or pagination. The output schema helps, but the overall guidance feels slightly incomplete for full agent decision-making.

  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 description adds significant meaning for 10 of 12 parameters, explaining units, filter semantics, and naming sources. It does not explain `limit` or `query_text`, which remain ambiguous gaps despite 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 clearly states the tool's purpose: 'Recherche des treks' (search treks) on the GeoTrek instance. It distinguishes itself from sibling list tools by focusing on searching with filters rather than listing available values.

  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 provides context on how to use filters, notably referencing list_labels and list_activities for valid names, and explains the two geographic proximity options. It does not explicitly contrast with alternatives, but the intent is clear given the sibling tools are list tools.

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