Server Quality Checklist

Tool Scores

• keap_list_notesB
  3.1/5.0
  Behavior2/5

  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 only reveals 'API: GET /notes,' implying a read-only operation, but omits auth requirements, rate limits, ordering, and other runtime behaviors. This adds minimal value beyond the name and 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 extremely concise and front-loaded, with no filler. The API reference and argument list are scannable and every sentence earns its place.

  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?

  An output schema exists, so return values are covered. The description does include filter options and pagination parameters, making it reasonably complete for a simple list endpoint. However, it is thin on usage context and behavioral caveats, though the low complexity and lack of required parameters keep it acceptable.

  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 0%, so the description must compensate. It does list all four parameters with brief explanations, e.g., 'Filter by contact ID' and 'Pagination offset,' which clarifies the semantics slightly beyond the bare parameter names. However, the meanings are largely self-evident and lack deeper detail about formats or relationships.

  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 begins with 'List notes,' clearly indicating a resource-oriented read operation. It is distinguishable from siblings like keap_create_note and keap_list_contacts, though the type of notes (e.g., contact notes vs. opportunity notes) is not explicitly stated.

  Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

  Usage Guidelines2/5

  Does the description explain when to use this tool, when not to, or what alternatives exist?

  No guidance is provided on when to use this tool versus alternatives, nor any exclusions or prerequisites. The description simply restates the action and parameters, leaving the agent to infer usage from the tool name.

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

• keap_create_opportunityB
  3.4/5.0
  Behavior2/5

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

  With no annotations, the description carries full responsibility for behavioral disclosure. It only states it creates an opportunity and lists parameters; it doesn't mention permissions, idempotency, response behavior, or side effects. The API line adds minimal context beyond what the name implies.

  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 efficiently organized: a one-line purpose, the API path, then a bullet-like list of parameters. No wasted words, though the API line is marginally redundant with the tool name. Front-loaded with the core intent.

  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?

  The tool is a create operation with 10 parameters and an output schema, so parameter coverage is high. However, it lacks any usage guidance, behavioral context (e.g., whether revenue ranges are inclusive, how dates are interpreted), or caveats. Acceptable but with clear gaps for a tool of this complexity.

  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 zero description coverage for its 10 parameters, but the tool description compensates by providing one-line explanations for each parameter, including which are required (though the schema already marks those). This gives the agent meaningful semantics beyond raw type 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 opens with 'Create a sales opportunity (deal)' – a specific verb and resource. It also names the underlying API endpoint, making the action unambiguous and distinct from sibling tools like keap_get_opportunity or keap_list_opportunities.

  Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

  Usage Guidelines2/5

  Does the description explain when to use this tool, when not to, or what alternatives exist?

  The description gives no guidance on when to use this tool versus alternatives. It does not mention exclusions, prerequisites, or typical scenarios. It only lists parameters, leaving the agent to infer usage from the tool name and sibling context.

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

• keap_list_usersB
  3.4/5.0
  Behavior3/5

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

  With no annotations provided, the description carries the burden of behavioral disclosure. It does reveal the operation is a GET request (read-only) and includes pagination parameters, but it omits details about authentication, rate limits, or default behaviors of filters like include_inactive or include_partners.

  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 and well-structured, leading with the core purpose and then providing the API endpoint and parameter definitions. Every line is relevant, and there is no wasteful or redundant 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?

  For a simple list operation with optional pagination and filter parameters, the description provides sufficient detail to understand what the tool does and how to invoke it. The existence of an output schema covers return values, so the lack of explicit return documentation is acceptable.

  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 has no descriptions (0% coverage), so the description's Args section attempts to explain each parameter. It adds minimal meaning (e.g., 'Max results per page' for limit) but largely restates the parameter names, offering only basic clarification.

  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 'List users of the Keap app', providing a specific verb and resource. It distinguishes itself from sibling tools that list other entities (contacts, tags, etc.) by focusing on users, though it does not explicitly contrast with any particular sibling.

  Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

  Usage Guidelines2/5

  Does the description explain when to use this tool, when not to, or what alternatives exist?

  The description provides no guidance on when to use this tool versus alternatives. It does not mention any exclusions, prerequisites, or comparisons with sibling list tools, leaving the agent to infer usage solely from the tool name.

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

• keap_create_taskA
  3.6/5.0
  Behavior2/5

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

  With no annotations, the description carries the burden. It reveals the API method (POST /tasks) and implies a write operation, but lacks details on side effects, permissions, error conditions, or response behavior. No additional context provided beyond the basic action.

  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 well-structured and front-loaded. It opens with the core action, states the API, and then lists parameters in a readable format. Every sentence adds value; no fluff or redundancy.

  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 with 8 parameters and no schema descriptions, the description covers all parameters and highlights required fields. It also notes the API endpoint and date format. The absence of return value explanations is mitigated by the existence of an output schema. It is sufficiently complete for an agent to invoke the tool correctly, though it could mention typical failure modes.

  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 0% description coverage, so the description compensates by providing brief explanations for all 8 parameters. For example, it clarifies due_date format (ISO 8601) and lists allowed values for remind_time. However, some descriptions are generic (e.g., 'priority: Task priority') and could be more specific.

  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 task' with a specific verb and resource, distinguishing it from sibling tools like keap_list_tasks (listing) and keap_create_note. It is concise and unambiguous.

  Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

  Usage Guidelines2/5

  Does the description explain when to use this tool, when not to, or what alternatives exist?

  No explicit guidance on when to use this tool versus alternatives. It does mention required fields ('Must include at least a title and due date'), but does not explain when to choose this over other task-related operations or provide exclusions.

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

• keap_get_opportunityA
  3.7/5.0
  Behavior2/5

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

  No annotations are provided, so the description must carry the full burden. It discloses the API endpoint and the optional_properties parameter, but it does not mention error behavior (e.g., 404 not found), default fields returned, authentication needs, or any side effects. This is a significant gap for a retrieval tool.

  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 and well-organized: a one-line purpose, the API reference, and an Args block. Every line adds value without redundancy or unnecessary detail.

  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?

  The tool is a simple retrieval operation with an output schema, so the description does not need to explain return values. However, it is missing guidance on when to use it versus other tools and lacks behavioral details like error handling, making it only partially complete for an agent.

  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 input schema only provides types and titles, but the description adds meaningful context: opportunity_id is 'the opportunity's unique ID' and optional_properties is a 'comma-separated list of extra fields to include.' This clarifies the purpose and format of both parameters, going beyond what the schema offers.

  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 'Retrieve a single opportunity by ID,' which is a specific verb+resource statement that clearly distinguishes this tool from siblings like keap_list_opportunities. It also provides the exact API endpoint, reinforcing its purpose.

  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 this tool is for fetching a single opportunity by ID, but it does not explicitly mention when to use it over alternatives (e.g., keap_list_opportunities) or provide any exclusions. The usage context is present but not elaborated.

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

• keap_list_tasksA
  3.7/5.0
  Behavior2/5

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

  With no annotations provided, the description carries full responsibility for behavioral disclosure. It only lists parameters and the HTTP method; it does not state whether this is a read-only operation, what the default scope is (e.g., all account tasks vs. user-specific), or any pagination behavior beyond the parameter names.

  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 efficient: a short statement, an API line, and a structured Args list. Every line earns its place with no fluff or repetition. The numeric/boolean filters are each described in a single concise phrase.

  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?

  An output schema exists, so return values don't need explanation. The description covers filter parameters and pagination inputs, but misses broader context: whether the tool lists all tasks in the account or only those visible to the authenticated user, how filters combine, and default sort behavior. It is minimally viable but has clear gaps.

  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 documenting all 7 parameters with one-line explanations (e.g., 'contact_id: Filter by related contact ID'). This adds meaning beyond the schema. However, 'order: Sort field' is vague regarding accepted values and syntax, and 'completed' doesn't mention boolean type, so not perfect.

  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 'List tasks' – a specific verb and resource. It distinguishes from sibling tools like keap_create_task (create) and keap_list_contacts (different resource). Including 'API: GET /tasks' reinforces the exact operation.

  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 verb 'List tasks' implies usage when needing to retrieve task data. However, it offers no explicit guidance on when to use this vs. alternatives like keap_list_notes or keap_list_contacts, nor any exclusions or prerequisites.

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

• keap_list_tagsA
  3.9/5.0
  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 of behavioral disclosure. It only states 'List all tags' and lists filters; it does not mention whether this is a read-only operation, any authentication requirements, rate limits, or pagination behavior beyond the parameter definitions. The verb 'list' implies a read, but no explicit safety or side-effect information is given, which is a significant gap given the lack of 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?

  The description is succinct and front-loaded with the core purpose. The API endpoint and argument list are useful and well-organized. No extraneous fluff; every line contributes. It could be slightly more concise by omitting the API endpoint, but it does not hurt and may help some agents.

  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 a read-only list operation, four optional filters, and an output schema present, the description is largely complete for selection and basic invocation. It covers the main behavior and parameter meanings. It does not explicitly mention the default pagination or return format, but those are handled by the schema defaults and output schema. The main gap is the lack of usage guidance relative to sibling tools, which is already partially covered by the purpose clarity.

  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 input schema has zero description coverage, so the description's argument explanations are essential. It provides concise meanings for each parameter: filter by category ID, filter by name, max results per page, and pagination offset. This adds meaningful context that the schema lacks, though it could go further (e.g., exact match vs partial match). Still, it compensates well for the schema's silence.

  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 starts with 'List all tags defined in the app' which clearly specifies the verb (list) and resource (tags), and the scope 'defined in the app' distinguishes it from contact-specific tag listings like those in sibling tool keap_list_contact_tags. This is a specific, unambiguous 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 gives clear context that this lists all app-level tags, which contrasts with keap_list_contact_tags (likely for tags on a contact). It does not explicitly name alternatives or exclusions, but the 'defined in the app' phrasing implicitly guides the agent to use this for global tag lookup rather than per-contact tags. The filter arguments also hint at typical use cases (e.g., filtering by category or name).

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

• keap_create_contactA
  4/5.0
  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. It discloses the HTTP method (POST) and the validation requirement, but does not mention side effects, error behavior, permissions, idempotency, or what happens on duplicate creation. This is a significant gap for a mutation tool.

  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-organized with a concise summary, an API reference, and a structured argument list. Each line serves a purpose, but the list format and multi-line address example add some length. It is appropriately sized for the number of parameters and not wasteful.

  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 has 6 parameters and no annotations, the description adequately covers all parameters with examples and states the core validation rule. An output schema exists, so return values are not needed. However, it omits any mention of permissions, error handling, or behavior beyond creation, which would improve completeness.

  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 0% description coverage, but the description compensates fully. It explains each parameter (given_name, family_name, email_addresses, phone_numbers, addresses, custom_fields) with clear definitions and example structures, making the intended format explicit and actionable.

  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 begins with 'Create a contact,' which clearly identifies the specific action and resource. It is distinct from sibling tools like keap_create_opportunity, keap_create_note, and keap_create_task, and the verb+resource pattern is unambiguous.

  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 states a prerequisite: 'Must include at least one email address or phone number.' This provides clear context for when the tool can be used. It does not explicitly mention alternatives or when not to use it, but the purpose is self-evident given the sibling tools cover other operations.

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

• keap_list_contact_tagsA
  4.1/5.0
  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 includes the API endpoint and mentions pagination via limit/offset, which adds some value. However, it does not explicitly state the read-only nature, error handling, auth requirements, or response format, leaving room for more transparency.

  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 and well-structured: a clear opening statement, the API endpoint, and a bulleted list of arguments. Every line earns its place with no filler, making it efficient and easy to parse.

  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 operation with an output schema available, the description covers the core purpose and parameters. It lacks deeper behavioral details like error scenarios or rate limits, but these are partially covered by the simplicity of the operation and the presence of an output schema.

  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 no per-property descriptions (0% coverage), so the 'Args' section in the description fully compensates by explaining each parameter: contact_id, limit, and offset with clear meanings. This provides all necessary semantic context.

  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 'List the tags applied to a contact', which identifies the action (listing) and resource (tags on a specific contact). This distinguishes it from sibling tools like keap_list_tags (likely all tags) and keap_apply_tags_to_contact (modifying tags).

  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 context of use is implied by the purpose statement—retrieve tags for a contact—but there is no explicit guidance on when to use this tool versus alternatives, nor any exclusion criteria. No comparison with sibling tools is provided.

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

• keap_list_opportunitiesA
  4.1/5.0
  Behavior3/5

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

  Annotations are absent, so the description bears the full burden. It discloses the API method (GET), filter semantics, and sort options, which is useful. However, it does not explicitly state that this is a read-only operation, mention authentication requirements, or describe edge cases like pagination behavior beyond offset/limit. The read-only nature is implied by 'List' but not explicitly confirmed.

  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 compact and well-structured: a one-sentence purpose, the endpoint, and a bullet-style Args list. It is front-loaded with the core function and every line adds value without redundancy.

  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 (6 optional parameters) and existence of an output schema, the description covers the essential aspects: purpose, endpoint, and all parameter meanings. It lacks minor details such as default sorting direction or search behavior, but is generally complete for invoking the 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?

  Schema description coverage is 0%, but the description provides meaningful explanations for all six parameters, including filter semantics and sort field examples. This fully compensates for the missing schema descriptions, giving the agent clear guidance on how to construct calls.

  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 'List sales opportunities (deals)' using the specific verb 'list' and resource 'opportunities', distinguishing it from sibling tools like get_opportunity and create_opportunity. It also specifies the API endpoint, which reinforces its purpose.

  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 the tool is used for listing opportunities and provides filter parameters, but it does not explicitly state when to use this tool over alternatives such as get_opportunity or create_opportunity. There is no exclusionary guidance or comparison with siblings.

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

• keap_get_contactA
  4.2/5.0
  Behavior3/5

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

  Since no annotations are provided, the description carries the burden. It uses the word 'Retrieve' and shows a GET endpoint, which implies a safe read operation, but it does not disclose behavior around missing contacts, authentication requirements, or rate limits. For a simple read tool this is minimal but perhaps adequate.

  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 concise and includes only relevant details. The 'API:' and 'Args:' formatting is a bit unusual but still structured and front-loaded. It earns its place without verbosity.

  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 output schema exists (so return format is covered), the description sufficiently explains the action and parameters. It lacks error-handling notes or edge-case behavior, but for a straightforward GET-by-ID tool, this is close to complete.

  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 provides no descriptions (0% coverage), but the description fully compensates. It explains contact_id as the unique ID and optional_properties as a comma-separated list with an example, which is more informative than many schema descriptions.

  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 'Retrieve a single contact by ID,' which is a specific verb-resource pair that clearly distinguishes it from the sibling list tool (keap_list_contacts) and other resource-specific tools. The mention of 'single' explicitly differentiates from listing.

  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 context is clear: it should be used when you have a specific contact ID and need that single contact's data. However, it does not explicitly mention alternatives or when not to use it, such as when you need multiple contacts and should use keap_list_contacts.

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

• keap_apply_tags_to_contactA
  4.3/5.0
  Behavior3/5

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

  The description discloses the HTTP method (POST) and identifies the operation as applying tags, which implies a write/mutation action. However, it does not elaborate on side effects, authentication requirements, or potential errors, leaving some behavioral details undisclosed. Given no annotations are present, this is a moderate level of transparency.

  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 compact and well-structured, leading with the core action, followed by the API endpoint and a clear Args list. Every sentence contributes valuable information without redundancy.

  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 mutation tool with an output schema, the description provides the essential operation and parameter details. It lacks explicit usage guidance and deeper behavioral context, but overall it is sufficiently complete for making an informed invocation decision.

  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 input schema has no descriptions (coverage 0%), and the description compensates fully by defining both parameters: contact_id as 'The contact's unique ID' and tag_ids as 'Required. List of tag IDs to apply.' This adds meaningful semantic detail that the schema 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?

  The description opens with a clear, specific verb phrase 'Apply one or more tags to a contact,' which unambiguously states the tool's purpose. It distinguishes itself from sibling tools like keap_list_tags and keap_get_contact by focusing on the mutation of a contact's tags.

  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 when to use the tool: whenever tags need to be applied to a contact. It does not explicitly mention alternatives or exclusion criteria, but the context is clear enough given the sibling tools, and no competing apply-tag tool exists.

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

• keap_create_noteA
  4.3/5.0
  Behavior3/5

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

  With no annotations, the description carries the full burden of behavioral disclosure. It adds the validation constraint (must include title or body) and the allowed enum values for type, which are useful. However, it does not disclose error behavior, permissions, idempotency, or side effects, leaving notable gaps in transparency for a mutation tool.

  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 structured with a clear opening line, an API reference, and an Args list. It is slightly longer than necessary—the API endpoint line could be omitted as it adds little for an agent—but it remains readable and front-loaded with the core purpose. Every sentence serves a purpose, so it earns a 4.

  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 5-parameter schema with 1 required, the description covers all parameters with additional context and includes a validation rule. The presence of an output schema covers return values. The combination of description and schema provides a complete picture for correct invocation, making this a well-rounded tool definition.

  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 coverage is 0%, so the description's Args list is essential. It explains each parameter, including the required contact_id, the meaning of user_id, and the allowed values for type. This fully compensates for the schema's lack of descriptions and adds significant value beyond the field titles.

  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 action ('Create a note on a contact') with a specific resource, distinguishing it from sibling tools like keap_list_notes (list vs create) and keap_create_task (task vs note). The additional validation rule about requiring at least a title or body further clarifies the tool's exact 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 provides a clear context for creating a note and gives a prerequisite ('Must include at least a title or body'). It does not explicitly mention alternatives or when not to use it, but the sibling tools are distinct CRUD operations and the purpose is clear enough to guide selection. This is clear context with no explicit exclusions, warranting a 4.

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

• keap_list_campaignsA
  4.3/5.0
  Behavior4/5

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

  No annotations are provided, so the description carries the burden. It discloses the HTTP method (GET), which signals a read-only operation, and gives parameter meanings. It does not mention pagination behavior or response shape, but the output schema likely covers the latter.

  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 compact and well-organized with a clear purpose statement, API endpoint, and parameter list. There is no redundant text; every line adds value.

  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, the description covers the essential aspects: purpose, endpoint, and parameter semantics. The presence of an output schema handles return value documentation, making this description sufficient.

  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 input schema has no property descriptions (0% coverage). The description adds concise explanations for all four parameters, including examples for the 'order' field, fully compensating 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 'List marketing/automation campaigns' which is a specific verb+resource. This distinguishes the tool from sibling tools that list contacts, opportunities, notes, tasks, and users.

  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 provides only the basic purpose and parameter list; it does not explicitly state when to use this tool over alternatives. Since there is no other campaign-related tool among siblings, usage is implied but not explicitly contrasted.

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

• keap_list_contactsA
  4.3/5.0
  Behavior4/5

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

  With no annotations, the description carries the behavioral disclosure burden. It explicitly identifies the operation as an API GET, which signals a read-only action, and discloses pagination behavior with default limit and offset. It does not mention rate limits or exact match semantics, but for a simple list operation the core behavior is transparent.

  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 compact and front-loaded with the purpose, followed by an API reference and a clear Args list. Every line adds value, and the parameter explanations are necessary given the zero schema coverage. No filler or redundancy.

  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 existing output schema, the description need not explain return values. It covers the endpoint, all parameters, and pagination/sort behavior, making the tool invokable. It could have explicitly stated that all filters are optional or how multiple filters combine, but the defaults in the schema largely fill that gap.

  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 must fully compensate. It provides a clear, human-readable explanation for all six parameters, including 'Filter by first name', 'Max results per page (default 20)', and sort field examples. This adds meaning beyond the bare schema titles and types.

  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 begins with 'List contacts', a specific verb+resource that clearly identifies the tool's function. It distinguishes itself from sibling tools like keap_get_contact (single contact), keap_create_contact, and keap_list_contact_tags. The 'API: GET /contacts' line further reinforces the exact operation.

  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 through the verb 'List' and the filter/pagination parameters, but it does not explicitly state when to use this tool versus alternatives such as keap_get_contact for a single contact. No exclusions or alternative recommendations are provided, so usage guidance is only implicit.

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