Server Quality Checklist

Tool Scores

• search_kbA
  4.6/5.0
  Behavior5/5

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

  Discloses that excerpts are returned verbatim without summarization, enabling citation. Annotations already indicate readOnly and idempotent; description adds retrieval behavior and error context.

  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, front-loaded purpose, and minimal redundancy. Slightly long but every sentence adds value.

  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?

  Covers purpose, query strategy, not-do list, error handling, and output format. Sufficient for an agent to select and use correctly, especially given output schema exists.

  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 coverage is 0%, but description explains how to formulate queries (using content words) and implies that limit and category are optional. However, no explicit parameter descriptions are given.

  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 it searches the knowledge base for procedure/policy, returns ranked excerpts, and distinguishes itself from sibling tools like search_tickets and draft_response.

  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?

  Provides explicit guidance on when to use (for procedures/policies), how to query (use keywords not sentences), what it does not do, and error handling (KB_NO_MATCH).

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

• draft_responseA
  4.8/5.0
  Behavior5/5

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

  Disclosures go far beyond annotations (readOnlyHint, idempotentHint). Details the security guardrail (two independent checks, indicators, non-negotiable). Explains return behavior, error conditions, and what it does not do. No contradiction with annotations.

  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 headings and bullet points. Front-loaded with core purpose. Somewhat lengthy but every section adds essential value (security, limitations, errors). Could trim redundant phrasing slightly.

  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?

  Comprehensive: covers all error cases, security guardrail with detailed indicators, return value composition (references output schema), usage boundaries, and escalation path. Output schema exists so return format documentation is not required in description.

  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?

  Only one parameter (ticket_id). Schema coverage is 0% but the description implicitly ties the parameter to its purpose ('for a ticket'). Does not add explicit syntax or constraints but sufficient given simplicity of 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 opens with a clear verb ('Compose') and resource ('knowledge-base-grounded draft reply for a ticket'). It distinguishes itself from siblings like search_kb (searching vs drafting) and update_ticket (no state change).

  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 states when to use the tool: to draft a KB-grounded reply. Provides clear do's and don'ts (e.g., do not invent facts, do not attempt to work around refusal). Offers actionable guidance on errors and what to do on security refusal.

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

• update_ticketA
  4.9/5.0
  Behavior5/5

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

  Annotations indicate idempotentHint=true and destructiveHint=false, which align with the description's confirmation gate and non-destructive dry run. Description adds context: dry run returns `applied: false` and a `changes` list, note appends rather than replaces, omitted fields are left unchanged. No contradictions.

  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 long but well-structured with bold headers, bullet points for field values and errors. Every sentence adds value, though some redundancy (e.g., repeating 'confirm=true' instructions) could be trimmed. Front-loaded with main function and key warning.

  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 5 sibling tools, the description thoroughly covers when to use, field values, error cases, and what the tool does not do. Output schema exists so return values are handled. No gaps; the tool is fully specified.

  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 has 0% description coverage, but the description fully compensates: it lists allowed values for status, priority, tier, assignee, and note, explains the confirm parameter's role, and clarifies that omitted fields are untouched. Adds meaning 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?

  Clearly states the tool changes ticket state: status, tier, priority, assignee, or an appended note. Explicitly distinguishes from siblings by listing what it does NOT do (e.g., does not send to requester, does not delete tickets), which differentiates it from search_tickets, get_ticket, and draft_response.

  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?

  Provides explicit, step-by-step usage guidance: dry run first with confirm=false, show preview to user, get agreement, then call with confirm=true. Also warns against assuming user intent. Separates the confirmation gate from batching and explains error handling like CONFIRMATION_REQUIRED.

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

• get_ticketA
  5/5.0
  Behavior5/5

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

  Adds behavioral context beyond annotations: explains limitations (category field may misdescribe, does not assess safety), error details, and format of ticket IDs. No contradiction with annotations.

  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?

  Concise yet comprehensive: uses bullet points and clear sections ('WHAT IT DOES NOT DO', 'ERRORS') to efficiently convey purpose, usage, and caveats without redundancy.

  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?

  Fully covers what the tool returns (full ticket with body), what it does not, and how it fits into the workflow (after search_tickets, before draft_response). Output schema exists, so return format details are not 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?

  Compensates for 0% schema parameter description by clarifying context for ticket_id (use after search, ID format like 'T-014') and error handling, adding significant meaning beyond the input 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?

  Explicitly states 'retrieve one ticket in full' and highlights the unique feature of returning requester's message body, distinguishing it from sibling tools like search_tickets.

  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?

  Gives clear when-to-use ('once you have a specific ticket ID — typically from search_tickets') and what it does not do (no triage, no safety determination), contrasting with draft_response.

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

• search_ticketsA
  5/5.0
  Behavior5/5

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

  Discloses limitations: no ticket bodies, unreliable classification, query matching only substrings without ranking. Explains error handling (empty result vs truncated). Annotations already readOnly, idempotent; description adds behavioral context beyond annotations.

  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?

  Well-structured with clear sections: what it does, what it does not do, filter values, errors. No redundant sentences, efficient and thorough.

  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?

  Covers all aspects: filtering, ordering, limits, return format (compact summaries, total_matched, truncated), and error conditions. Output schema exists so return values are not required, but description still explains them. Fully adequate for this complex 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?

  Despite 0% schema coverage, description provides detailed filter values and allowed enums for each parameter (status, priority, tier, category, client, query). Adds meaning that the bare schema (type, default) lacks.

  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?

  Clearly states it finds tickets in Summit Managed IT queue using filters. Distinguishes from siblings get_ticket (full text) and search_kb (procedures). Explicit about what it does not do.

  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?

  Provides explicit when-to-use and when-not-to-use scenarios, including alternatives like get_ticket for full text and search_kb for procedures. Explains filter combination (AND) and empty result behavior.

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