Server Quality Checklist

Tool Scores

• draft_outreach_emailA
  3.8/5.0
  Behavior3/5

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

  With no annotations provided, the description bears full transparency responsibility. It discloses the underlying endpoint (POST /api/v1/outreach/draft), the model used (claude-sonnet-4-6), and return fields (subject, body, confidence score, reasoning), which is valuable. However, it does not explicitly state whether the draft persists, whether the POST is read-only or state-changing, or any potential side effects like quota consumption, leaving key behavioral traits undisclosed.

  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 four concise sentences, front-loaded with the primary purpose first. Every sentence adds distinct value: purpose, implementation detail (endpoint), model specification, and return payload. There is no redundant phrasing or filler, making it highly skimmable.

  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?

  For a tool of moderate complexity, the description covers the essential aspects: what it does, how it works (endpoint/model), and what it returns. The lack of an output schema is mitigated by explicitly listing the return fields. Minor gaps exist around edge cases (e.g., invalid guestId), but overall this is adequately complete for an independently useful tool.

  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%, with each parameter already having a meaningful description (e.g., 'Guest ID to draft outreach for'). The tool description adds no extra parameter-level meaning beyond what the schema provides, so the baseline of 3 applies without any significant upward adjustment.

  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 'Generate an AI outreach email draft for a guest,' clearly stating a specific verb, resource, and audience. It further distinguishes itself from sibling tools (list_guests, add_guest, etc.) by focusing on email drafting rather than guest CRUD or analytics, making its purpose unmistakable.

  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?

  Usage context is implied by the tool name and the verb 'Generate'—an agent can infer when to invoke it, but there is no explicit when-to-use or when-to-avoid statement. No alternatives are mentioned, nor are prerequisites like 'guest must exist in the system' or 'use after list_guests to obtain guestId,' leaving room for misinterpretation.

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

• get_analytics_summaryA
  4/5.0
  Behavior3/5

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

  No annotations are provided, so the description carries the transparency burden. It discloses that it wraps a GET endpoint, implying a read-only operation, and lists the returned data fields. However, it does not mention authentication, rate limits, or any side effects, though for a simple analytics overview this may be sufficient.

  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, front-loaded with 'Dashboard overview', and clearly lists the included metrics in a compact manner. It conveys necessary information without unnecessary words.

  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 simplicity (no parameters, no output schema), the description is complete: it lists the key data points provided. The sibling tool names reinforce that this is the analytics-specific tool. It could be slightly more explicit about the intended use case, but it is adequate.

  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, so the description need not explain parameter meaning. The schema is trivially complete with 100% coverage. Baseline for 0 params is 4, and the description adds no conflicting or missing param info.

  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 a dashboard overview with specific metrics (total guests, stage breakdown, average fit score, conversion rates, etc.). The mention of the underlying GET endpoint reinforces its purpose. It is distinct from sibling tools like list_guests or draft_outreach_email.

  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 for high-level analytics summaries but does not explicitly state when to use it over alternatives or provide exclusion criteria. It is clear context but lacks explicit guidance on when not to use it.

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

• list_guestsA
  4/5.0
  Behavior3/5

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

  With no annotations, the description carries the full burden. It discloses pagination, filterability, and that it wraps a GET endpoint, which implies read-only behavior. However, it does not mention what is returned (e.g., format, default ordering), rate limits, or other behavioral nuances. It 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.

  Conciseness5/5

  Is the description appropriately sized, front-loaded, and free of redundancy?

  Two sentences, front-loaded with the main verb and resource, followed by additional capabilities. No redundant words or fluff. The description is concise 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?

  For a simple list tool with a fully described schema (all 5 params documented, enums provided) and no output schema, the description is sufficient. It covers pagination and filters, and the sibling context is clear. It omits some details like response shape, but for a list endpoint this is a minor gap.

  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%, so the baseline is 3. The description mentions stage, priority, and free-text search but does not add meaning beyond the schema. It aligns with page/limit via 'paginated' but does not clarify defaults or syntax beyond what the schema already states.

  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's function: 'List guests in the pipeline', with specific attributes (paginated, filterable by stage, priority, search). It distinguishes from sibling tools like add_guest or update_guest_stage by focusing solely on listing. The mention of the GET endpoint reinforces its read-only nature.

  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 implies this tool is for retrieving/filtering guest data through 'List guests in the pipeline' and mentions pagination/filters. It provides clear context but does not explicitly name alternative tools or state when not to use it. Sibling tools like add_guest are obviously different, but there is no explicit exclusion.

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

• add_guestA
  4.2/5.0
  Behavior4/5

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

  With no annotations, the description carries the transparency burden. It discloses that fit scoring runs asynchronously and advises checking list_guests later, which is key behavioral information. It doesn't cover all edge cases like error handling or idempotency, but the most important behavior is surfaced.

  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 three sentences, each with distinct value: purpose, API wrapper, and async behavior guidance. There is no fluff or redundancy, and the key information is 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?

  The tool has no output schema, but the description covers the main use case and a key behavioral nuance (async fit scoring). It lacks explicit return-value details, but the follow-up guidance compensates. The context is sufficient for an agent to understand the tool's role and next steps.

  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 input schema provides descriptions for all 7 parameters (100% coverage), and the tool description does not add parameter-specific semantics beyond that. The description's mention of 'discover stage' is a general context, not tied to a parameter, so baseline 3 applies.

  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 'Create a new guest in the discover stage,' providing a specific verb, resource, and stage. It also maps to the underlying API endpoint (POST /api/v1/guests), and the action is distinctly different from sibling tools like list_guests or update_guest_stage.

  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 gives clear context for using the tool to create a guest and provides follow-up guidance to call list_guests or the detail endpoint to see fitScore. It doesn't explicitly exclude alternatives, but the create action is unambiguous among siblings.

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

• update_guest_stageA
  4.4/5.0
  Behavior4/5

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

  With no annotations, the description carries the full burden of behavioral disclosure. It discloses the HTTP method (PATCH), the allowed transition paths, and the behavior that invalid transitions are rejected by the API. It does not mention potential side effects, permission requirements, or reversibility, but the detailed transition rules provide substantial context beyond a generic 'update' statement.

  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 two sentences, front-loaded with the primary action, and the second sentence packs the transition rules into a compact, readable list. There is no fluff; every element adds necessary information about how the tool works.

  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?

  The description fully covers the tool's state-machine logic and API endpoint, which is the core complexity. However, it does not mention the response format or any side effects, and there is no output schema to fill that gap. Given the absence of annotations, a little more detail on expected return value would make it complete, but it remains adequate for invoking the tool correctly.

  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 100% description coverage, so the baseline is 3. The description adds meaningful semantics by defining the allowed transition paths, which clarifies constraints on the 'stage' parameter beyond the simple enum listing. It doesn't add extra detail for 'id' or 'reason', but the schema already covers those adequately.

  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's function with a specific verb ('Transition'), a resource ('a guest'), and a scope ('to a new lifecycle stage'). It also lists valid transition paths, which distinguishes it from sibling tools like list_guests and add_guest. The purpose is unambiguous and specific.

  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 the valid forward and backward transition paths, which serve as implicit guidance on when this tool is appropriate (i.e., whenever a guest's stage needs to change). It also notes that invalid transitions are rejected by the API, telling the agent it need not pre-validate. However, it does not explicitly mention alternative tools or edge cases where this tool should not be used, so it falls short of a 5.

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