Server Quality Checklist

Tool Scores

• search_peopleA
  4.5/5.0
  Behavior4/5

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

  With no annotations, the description carries the full burden. It discloses important behaviors: text filters are case-insensitive prefix matches with no wildcards, dictionary filters accept numeric IDs or Polish labels, and the return includes title, unit, and profile URL. It also notes the special case of a single match. However, it omits details like pagination, empty result behavior, and rate limits, preventing a perfect score.

  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 three paragraphs: purpose, filter semantics, and return usage. It is concise but dense, with each sentence adding value. Slightly longer than minimal, but justified by the tool's complexity.

  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 high parameter count and the presence of an output schema, the description covers the essential aspects: purpose, filter behavior, return fields, and the relationship to sibling tools. It does not explicitly explain the 'limit' parameter's effect or behavior with no criteria, but these are minor gaps for a search 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?

  Schema description coverage is 0%, so the description compensates by grouping all 14 parameters into text filters and dictionary filters, listing each explicitly. It explains that text filters are prefix matches and dictionary filters accept IDs or labels, adding meaning beyond the bare schema. However, it does not explain the 'limit' parameter or provide translations for the Polish field names.

  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 'Search AGH staff in the SkOs directory' with a specific verb and resource. It also distinguishes itself from siblings by referencing list_filter_options for browsing filter options and get_person for contact data, making the 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?

  Explicitly tells users when to use alternatives: 'use list_filter_options to browse them' for dictionary filters, and 'pass that url to get_person for contact data.' It also clarifies when the full profile is included, implying you may not need get_person for single matches.

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

• get_personA
  4.6/5.0
  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 responsibility for behavioral disclosure. It clearly states the operation is a fetch (read-only) and enumerates the data returned. It also gives concrete input format examples. It does not mention error handling, rate limits, or authentication, but for a simple read operation the essential behavior is sufficiently disclosed.

  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 extremely concise: one sentence for the purpose and one sentence for the parameter format, with an example. Every word adds value, and the most important information (what the tool does) is front-loaded. No filler or repetition.

  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?

  Given the tool's simple interface (one required parameter, no nested objects) and the presence of an output schema, the description is complete. It already states the return fields, so external users know what to expect. The parameter guidance is thorough, and the tool's low complexity means no additional context is needed.

  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 a single parameter 'person' with only a title and no description (0% schema coverage). The tool description fully compensates by explaining the parameter's meaning: 'profile url or slug as returned by search_people', and provides concrete examples. This goes far beyond the schema's bare definition and gives the agent the exact format required.

  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: 'Fetch a full SkOs profile,' followed by a list of fields returned (units, position, room, phones, email, www). This clearly distinguishes it from siblings like 'search_people' and 'list_filter_options' by emphasizing a single profile fetch rather than a search or filter operation.

  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 provides clear usage context by specifying that the 'person' parameter should be 'a profile url or slug as returned by search_people'. This implicitly tells the agent to first call search_people to obtain the identifier, then use get_person for the full profile. It does not explicitly mention when not to use the tool or name alternatives, but the input guideline is strong enough to convey the typical workflow.

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

• list_filter_optionsA
  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. It discloses key behaviors: the valid field values (enumerated) and the case-insensitive substring filtering for 'contains'. It doesn't mention side effects, but for a read-only list tool this is sufficient. It adds value beyond the schema.

  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 brief, front-loaded with the main purpose, and uses a clean two-part structure for parameters. Every sentence adds meaningful information without any waste.

  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 two-parameter tool with an output schema, the description is complete. It covers the tool's purpose, parameter semantics, and relevant constraints. No additional behavioral details (e.g., return format) are needed given the output schema exists.

  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?

  Schema description coverage is 0%, so the description fully compensates. It explains each parameter in detail: 'field' with a complete list of allowed values, and 'contains' with its optional, case-insensitive filtering behavior. This is far more informative than 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?

  The description states a specific action ('List allowed values') and resource ('dictionary filter of search_people'), clearly distinguishing it from sibling tools like search_people and get_person. It leaves no doubt about the tool's purpose.

  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 clearly implies the use case: when using search_people with a dictionary filter, you need to know allowed values. It doesn't explicitly exclude alternatives or say 'use this before search_people', but the context is straightforward and sufficiently clear.

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