Server Quality Checklist

Tool Scores

• collaborationB
  3.4/5.0
  Behavior3/5

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

  No annotations provided, so description carries full burden. It discloses pagination limits (max 50) and date formats (ISO), plus entity-specific filter constraints. However, it lacks safety disclosures (read-only vs destructive), error behavior, or rate limiting context that would be essential for a tool without annotation coverage.

  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?

  Well-structured with clear logical flow: purpose statement → action definitions → entity-specific filter reference. Information density is high with no redundant sentences. Bullet formatting (implied by hyphens) aids scanability for the complex filter matrix.

  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?

  Adequately covers input parameters and action selection for 10-parameter complexity, but lacks output schema description (return format, structure of events/tickets/posts objects). Without output schema or return value documentation, agents cannot predict result structure.

  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 100%, establishing baseline 3. The description organizes entity-specific filter constraints centrally (events vs tickets vs posts), but individual parameter descriptions in the schema already capture most of this specificity. Adds minimal semantic value beyond schema structure.

  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?

  States specific verb ('Query') + resource ('collaboration data in OfficeRnD') and distinguishes scope from siblings via entity types (events, tickets, posts). However, 'collaboration data' is slightly abstract without the entity list, and it doesn't explicitly contrast with sibling tools like 'community' or 'space'.

  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?

  Provides clear internal guidance distinguishing when to use 'list' (filtered pagination) vs 'get' (single entity by ID), including entity-specific filter mappings. However, it lacks external guidance on when to select this tool over siblings (billing, community, settings, space).

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

• settingsA
  3.5/5.0
  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. While 'Query' implies read-only behavior, the description doesn't explicitly confirm safety (crucial for a 'settings' tool), disclose pagination behavior beyond parameter existence, or describe return formats/error cases.

  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?

  Well-structured with clear section headers (action descriptions, entity-specific filters). Information is front-loaded with the general purpose statement followed by specific operational details. No redundant sentences, though the formatting with line breaks is slightly verbose.

  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 lack of output schema, the description should explain return values but doesn't. It adequately covers the 7-parameter complexity through the entity-filter mappings, but misses behavioral context (rate limits, auth requirements) that would complete the picture for a configuration 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?

  With 100% schema coverage, the baseline is 3. The description adds value by mapping specific filter parameters to their applicable entities (e.g., 'locations: name', 'business_hours: location'), clarifying constraints that the schema lists separately. It also emphasizes the 'locations only' restriction for the get action.

  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 'Query organization settings and configuration in OfficeRnD,' specifying the verb (query), resource (settings/configuration), and domain. It distinguishes from siblings (billing, collaboration, etc.) by focusing on configuration entities, though it doesn't explicitly contrast with them.

  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?

  Provides clear internal usage context by documenting when to use action=list versus action=get, explicitly noting that get is restricted to locations only, and mapping entity-specific filters. However, it lacks external comparison—no guidance on when to use this tool versus siblings like 'space' or 'community'.

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

• billingA
  4.1/5.0
  Behavior3/5

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

  With no annotations provided, the description carries the full burden. It successfully discloses pagination limits (max 50 per page) and date formats (ISO dates), but fails to explicitly declare the read-only/safe nature of the operations implied by 'Query', or mention rate limits and authentication requirements.

  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 clear action-based sections and efficient bullet-style listings for entity filters. It is appropriately front-loaded with the primary purpose statement. Minor density in the filter list prevents a perfect score.

  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 tool's complexity (13 parameters across 3 actions and multiple entities), the description adequately maps parameters to their applicable actions and entities. While it lacks output schema details, the rules indicate this is not required; however, it could briefly clarify what 'coin_stats' returns.

  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?

  Although schema description coverage is 100%, the description adds value by organizing parameters into entity-specific filter groups (payments, fees, plans) that are presented as a flat list in the schema. This contextual grouping helps agents understand which parameters combine logically.

  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 the specific verb 'Query' and resource 'billing/financial data in OfficeRnD', clearly distinguishing it from siblings like 'space', 'community', and 'settings'. It further clarifies scope by detailing the three distinct actions (list, get, coin_stats) and their specific purposes.

  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 guidance on when to use each internal action (list for filtered enumeration with pagination, get for single entity retrieval by ID, coin_stats for credit balances), effectively guiding selection between modes. However, it does not explicitly contrast with sibling tools or state when NOT to use this tool.

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

• spaceA
  4.1/5.0
  Behavior3/5

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

  With no annotations provided, the description carries the full burden. It discloses pagination limits (max 50 per page) and required fields for specific entities (seriesStart/End for booking_occurrences), but omits general behavioral traits like read-only safety, rate limits, or output format details.

  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 clear sections for actions and entity-specific filters. The entity filter list is lengthy but necessary given the 8 entity types supported; information is front-loaded with the primary purpose stated immediately.

  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 complexity (17 parameters, 8 entity types, 3 actions) and lack of output schema or annotations, the description comprehensively covers the input interface, action semantics, and entity-filter mappings. It adequately compensates for the missing output schema by detailing the query capabilities.

  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?

  While the schema has 100% description coverage, the description adds crucial enum values for the 'type' parameter (meeting_room|team_room|desk|etc.) that the schema lists only as a generic string. It also reorganizes parameters by entity type, making the polymorphic filtering logic clearer than the flat schema structure.

  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 'Query space/resource data in OfficeRnD,' providing a specific verb (Query), resource (space/resource data), and domain (OfficeRnD). It clearly distinguishes from siblings (billing, collaboration, community, settings) by focusing on physical workspace entities like resources, bookings, and floors.

  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 delineates the three actions (list, get, status) and their specific use cases, including constraints like 'status only for resources' and 'requires id.' However, it lacks explicit 'when not to use' guidance relative to sibling tools, though the domain separation is implicit.

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

• communityA
  4.3/5.0
  Behavior4/5

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

  No annotations provided, but description carries burden well: discloses pagination limits (max 50 per page), ISO date format requirements with examples, exact name matching constraints, and entity-specific operation restrictions (visitors only supports pagination). Missing explicit read-only safety declaration.

  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?

  Well-structured with clear sections for actions vs entity-specific filters. Front-loaded with purpose statement. Length is justified by the 9 entity types and their filter matrix, though the bullet list format is slightly verbose. No redundant or filler text.

  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?

  Comprehensive coverage of 13-parameter input space and entity-action logic compensates for missing output schema. Adequately addresses complexity without attempting to describe all possible return entity structures, which would be impractical. Missing annotations for safety/destructive hints.

  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 100% coverage, but description adds critical value: specific examples ('Yoan Reimers' not 'Yoan'), date usage patterns ('use these to get today's check-ins'), and reorganizes filter-entity mappings for readability. Adds semantic constraints beyond schema definitions.

  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?

  Opens with specific verb 'Query' and clear resource 'community/people data in OfficeRnD'. Distinct from siblings (billing=financial, space=physical locations, settings=config) through explicit domain focus on people/entities like members, companies, and visits.

  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?

  Provides clear internal guidance distinguishing 'list' (filters, pagination) from 'get' (single ID). Documents entity-specific filter availability and notes special cases (visitors/opportunity_statuses lack 'get' action). Lacks explicit cross-tool comparisons but domain separation from siblings is evident.

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