Server Quality Checklist

Tool Scores

• commune_france_profileB
  3/5.0
  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 behavioral burden. It states what kind of output profile is built, but it does not explain whether any resources are fetched, whether the operation is read-only, what side effects exist, or what the returned structure contains.

  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 concise, single-sentence, and front-loaded with the main action and resource. It avoids filler; the only minor weakness is that 'source-oriented' and 'geo identity' are not elaborated enough to make the description self-sufficient.

  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?

  With no output schema and no annotations, the description is the main informational source and it communicates the tool's result at a high level. It is adequate for a single-parameter profile builder, but an agent is still left guessing about return format, behavior, and exact input semantics.

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

  Parameters2/5

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

  The schema documents code_insee as a required 5-digit string, but the description provides zero parameter-level context. Since schema description coverage is 0%, the description was expected to compensate and at least link the INSEE code to the commune profile concept; it does not.

  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 names a specific action ('Build') and a clear resource ('commune profile'), and further specifies that the profile is source-oriented, includes geo identity, and suggests public-data queries. This gives enough semantic distinction from siblings like get_sources or find_commune, though it does not explicitly name them.

  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 usage context is implied: use this tool when a commune profile with geo identity and public-data query suggestions is needed. However, there is no explicit when-to-use versus alternatives guidance, and no warning against using sibling source-oriented tools for simpler lookups.

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

• commune_france_list_department_communesB
  3.1/5.0
  Behavior2/5

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

  There are no annotations, so the description carries the full burden of behavioral disclosure. It mentions the geo.api.gouv.fr dependency but does not state whether the call is read-only, whether it returns all or paginated data, what the response shape is, or any external failure/rate-limit considerations.

  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, front-loaded sentence with no filler or repetition. It states the action and target efficiently.

  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 and the single parameter is fully documented, so the description is minimally adequate for calling the endpoint. However, it lacks output-shape information and any interaction warnings, which is a noticeable gap given that there are no annotations and no response schema.

  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 fully documents department_code and includes an example. The description adds no extra parameter semantics, but at 100% schema coverage the baseline of 3 is appropriate.

  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 ('List') and a specific resource ('communes in a French department'), and names the external source. It is clear in what it does, though it does not explicitly differentiate itself from the sibling commune_france_find_commune, regardless of the fact that their scopes differ.

  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 given about when to choose this tool over commune_france_find_commune or the other siblings. The reader can infer the intended use from the description, but the only explicit guidance is what the tool does, not when to use it.

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

• commune_france_fetch_source_excerptB
  3.4/5.0
  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. It states the tool fetches an excerpt but does not disclose what happens when the source_key is not found, whether the excerpt is truncated at the nearest word boundary, or what the exact format of the excerpt is. It also doesn't mention any rate limits or other behavioral constraints.

  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 is concise and front-loads the primary action ('Fetch a short text excerpt') followed by the key parameter guidance. No wasted words.

  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?

  Given the tool has 2 parameters and no output schema, the description covers the core purpose and parameter semantics reasonably well. However, it is missing behavioral details like error handling, return format, and typical use cases, which an agent might need 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 schema has 2 parameters with 50% coverage (source_key has a description, max_chars does not). The description clarifies that source_key accepts an index, title keyword, or URL fragment, which adds meaning beyond the schema's generic description. It also implies max_chars controls the length of the excerpt, partially compensating for the schema gap.

  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 verb ('Fetch') and a specific resource ('a short text excerpt from a curated source'), and indicates it can be retrieved by index or title keyword. This distinguishes it from the sibling tools, which handle source listing, commune lookup, etc., though it doesn't explicitly name a sibling it is not.

  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 usage context by mentioning 'curated source' and by the sibling tools (e.g., 'commune_france_get_sources' likely lists available sources). However, it does not explicitly state when to use this tool versus the alternatives, nor does it give conditions like when to use a source index vs. a keyword.

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

• commune_france_find_communeA
  3.5/5.0
  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 indicates the underlying service (geo.api.gouv.fr) which gives some context about data source, but it does not mention behavior such as whether the query is fuzzy, case-insensitive, or how results are ordered. It doesn't disclose any limits (like the max limit parameter) or what happens when no commune is found. Moderate transparency for a read-only lookup 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?

  One concise sentence that captures the tool's purpose and data source without fluff. No wasted words, front-loads the action and resource, and includes the key identifiers. Appropriate length for a simple lookup tool.

  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 only two parameters and no output schema, so the description does not need to explain return values. However, it lacks context on the expected response format (e.g., list of communes with properties) and how to interpret the 'limit' parameter in filtering results. Given the lack of annotations and output schema, a bit more context on the query behavior would improve completeness.

  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 0%, and the description does not explain the parameters beyond the generic 'query'. The 'limit' parameter is self-explanatory from its schema (default, min, max), but the description does not clarify what format 'query' should take (e.g., partial name, full name, with accents). It adds minimal value over the schema, which only lists the parameter names and types.

  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 verb 'Resolve' and the resource 'French communes', and specifies the three supported query types (name, INSEE code, postal code). It distinguishes itself from siblings like list_department_communes (which lists by department) and get_sources (which gets data sources), though it doesn't explicitly name them. Clear purpose with good differentiation.

  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 the tool is for looking up communes by various identifiers, but it does not explicitly state when to use this tool versus alternatives like list_department_communes (when you have a department) or profile (when you have a specific commune). No exclusions or conditions are given. The context of 'resolve' suggests a search/find operation, but the when-not is absent.

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

• commune_france_get_sourcesA
  3.7/5.0
  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 of exposing behavior. It indicates a read-only listing operation and says nothing about destructive effects or hidden complexity, which is acceptable for a simple list tool. However, it lacks any detail about the response shape, size, or possible edge cases, though these are not critical for such a straightforward call.

  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 begins with the action word 'List' and then specifies the exact resource and context. Every word contributes, there is no redundancy, and it is appropriately sized for a simple no-parameter 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?

  Given the lack of parameters and an output schema, the description is contextually sufficient: the agent knows the call returns a list of curated sources used by this MCP. It does not describe the precise format of the returned list, but that is a minor omission for such a lightweight tool.

  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 description coverage is 100%, so there are no parameter meanings to clarify. The description adds no specifics because none are needed; the baseline for a parameterless tool 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 uses the concrete verb 'List' and identifies the resource as 'curated sources used by this MCP,' so the tool's object and action are clear. It does not explicitly distinguish itself from sibling tools, but the resource type (sources) is evidently different from commune-related operations, making the purpose understandable.

  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 about when to use this tool versus alternatives is given. The intended usage—retrieve the list of sources for the MCP—is implied from the description and the tool's name, but there is no mention of exclusions, prerequisites, or when a sibling tool would be more appropriate.

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