Server Quality Checklist

Tool Scores

• dpe_logementA
  3.9/5.0
  Behavior3/5

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

  No annotations provided, so description carries full burden. It discloses output fields and source (ADEME) but lacks details on behavior such as error handling, rate limits, or authentication needs. For a read-only query tool, the description is adequate but not rich.

  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?

  Description is concise with four lines plus an Args section that reiterates parameters with examples. Every sentence adds value, though the Args section partially duplicates schema info. Overall well-structured and 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?

  Tool has only two parameters and an output schema (present but not shown). Description explains key return fields. For its simplicity, coverage is good; lacks only minor details like error conditions or pagination.

  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 description compensates by explaining both parameters: code_postal as 5-digit zip code with example, adresse as optional text to refine. Adds meaningful context beyond the schema's type and default values.

  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 clearly states it returns DPE diagnostics with specific output fields (energy label, GES label, surface, consumption, date) and filtering by postal code and optionally address. This verb+resource definition distinguishes it from sibling tools like geocode_address or risques_immobilier.

  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?

  Description implies usage context by mentioning filtering by postal code and address, but does not explicitly state when to use this tool versus alternatives, nor provides exclusions or prerequisites. Sibling tools differ in function but no comparative guidance given.

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

• geocode_addressA
  4.1/5.0
  Behavior3/5

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

  No annotations provided, so description carries full burden. It describes return values but does not mention authentication, rate limits, error handling, or behavior for invalid addresses. For a read-only tool, basic transparency is adequate but could be improved.

  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 concise, using a short paragraph plus a structured docstring for parameters. Every sentence adds value, with no unnecessary information.

  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 annotations, one required parameter, and an output schema (present but not shown), the description covers key aspects: purpose, return values, and parameter usage. Lacks error handling details but is sufficient for a simple geocoding tool.

  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 includes a docstring for the 'adresse' parameter with an example ('8 boulevard du Port, Amiens'). Despite 0% schema coverage, this compensates well by explaining the parameter meaning and format.

  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 geocodes a French address using BAN and returns normalized address, coordinates, postal code, commune, and INSEE code. It distinguishes from siblings like dpe_logement, resolve_commune, and risques_immobilier by specifying its utility for targeting risks/DPE at the exact address.

  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 when geocoding French addresses but does not explicitly state when to use this tool versus alternatives or provide exclusion criteria. No guidance on prerequisites or when not to use.

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

• resolve_communeA
  4.4/5.0
  Behavior3/5

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

  No annotations provided, so description carries full burden. It describes the lookup behavior and return fields, but does not mention failure modes, rate limits, or authorization. Adequate but not rich.

  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 plus a parameter list. Front-loaded with purpose, no wasted words. Efficient and well-structured.

  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?

  With output schema present, description does not need to detail return values. Covers purpose, usage, and parameter adequately for a simple lookup tool. Slight lack of error handling info, but acceptable.

  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 has 0% description coverage, but the description provides an example ('Lyon', 'Combs-la-Ville') and clarifies the parameter is a commune name. Adds meaningful context beyond the raw 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?

  Description clearly states 'Résout une commune française par son nom' (verb+resource) and lists returned fields (code INSEE, département, etc.). It also distinguishes from siblings by positioning itself as the geographic anchor to use first.

  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?

  Explicitly says 'À utiliser en PREMIER, comme ancre géographique, avant les autres outils' and gives example of using code INSEE for risks. Provides clear when-to-use guidance.

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

• risques_immobilierA
  4.4/5.0
  Behavior4/5

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

  Without annotations, the description discloses that free addresses are automatically geocoded to identify the commune, a key behavioral trait. It does not mention error handling or response format, but this is partially covered by the output schema.

  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 well-structured with bullet points and clear sections, but includes slightly redundant phrasing. Every sentence adds value, so it is efficient but not ultra-concise.

  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?

  Covers input, purpose, and a behavioral nuance (geocoding). With an output schema present, it does not need to explain return values. Could mention whether multiple risks are aggregated, but overall complete for a risk-inspection tool.

  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?

  With 0% schema coverage, the description adds essential meaning: explains the parameter accepts either an INSEE code or free address, provides concrete examples, and clarifies the geocoding behavior. This fully compensates for the schema's lack of detail.

  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 provides natural and technological risks for a French commune, listing specific hazards (inondation, retrait-gonflement, séisme, etc.) and distinguishing it from siblings like dpe_logement, geocode_address, and resolve_commune.

  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?

  Explicitly advises consulting before a real estate purchase and explains acceptable inputs (INSEE code or free address). However, it does not explicitly mention when not to use the tool or suggest alternatives.

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