Server Quality Checklist

Tool Scores

• unassign_ticketB
  3.3/5.0
  Behavior2/5

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

  With no annotations, the description carries full transparency burden but only states the action and return type. It does not disclose side effects, permissions, or behavior if the ticket is already unassigned.

  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 efficient, using a structured docstring format with only essential information. No wasted words.

  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 simple (one param, no output schema), and the description covers the core purpose and return. However, it lacks information about error cases, side effects, or how it differs from related tools.

  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%, so the description must compensate. It documents ticket_id as required and describes it as 'the ID of the ticket to unassign', adding slight semantic value beyond the schema.

  Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

  Purpose5/5

  Does the description clearly state what the tool does and how it differs from similar tools?

  The description clearly states the action ('Unassign operator from ticket') with a specific resource (ticket in Tidio). It distinguishes itself from sibling tools as there is no other unassign tool.

  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 like update_ticket or delete_ticket. The usage is only implied by the purpose, not explicitly stated.

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

• delete_ticketA
  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 full burden. It states the return type ('Dict: A dictionary with success status') but fails to disclose permanence, irreversibility, cascading effects (e.g., deleting associated replies), or required permissions. The verb 'delete' implies destructiveness, but additional context is missing.

  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 succinct and front-loaded. The opening sentence states the purpose, followed by a compact Args section and a Returns note. Every sentence earns its place 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 one-parameter delete tool without an output schema, the description provides all essential invocation details (parameter meaning, requirement, and return shape). It falls short only in missing error behavior and usage guidance, which are less critical for such a straightforward operation.

  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 no parameter descriptions (0% coverage), but the description compensates by explaining ticket_id as 'Required. The ID of the ticket to delete.' This adds meaning beyond the parameter name and type, clearly linking it to the deletion action.

  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 ('Delete a specific ticket') and the resource ('ticket from Tidio'). It distinguishes from sibling tools like delete_contact and unassign_ticket by specifying the exact object and operation.

  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. For instance, it doesn't contrast with unassign_ticket or update_ticket, nor does it mention any prerequisites such as ticket existence or permissions.

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

• delete_contactA
  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 carries the full burden of behavioral disclosure. Although 'delete' implies a destructive action, the description does not state that the operation is irreversible, whether it is a hard or soft delete, or if any permissions are required. The only addition is a vague return format ('dictionary with success status'), which does not cover the safety implications of a mutating 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 extremely concise and well-structured. It leads with a one-sentence purpose, then uses a clear Args/Returns format. There is no wasted language, and every sentence contributes to understanding. The structure is ideal for quick parsing.

  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 that the tool has only one parameter and no output schema, the description covers the basic purpose, the parameter, and the return type. However, for a deletion tool, it lacks crucial contextual information such as the consequences of deletion (e.g., also deletes associated data), whether the action can be undone, and any prerequisites. While the simplicity helps, the lack of behavioral context makes it only minimally complete.

  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 must compensate. It does, by adding that contact_id is a UUID and that it is required, beyond the schema's type and required flags. This gives the agent a useful format hint. However, it does not explain how to obtain the UUID or the expected format (e.g., standard UUID vs custom string), which is a minor gap.

  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: 'Delete a specific contact (customer) from Tidio.' This uses a specific verb (delete) and resource (contact), distinguishing it from siblings like update_contact or create_contact. The scope is also clear (specific contact, identified by UUID).

  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 deleting a specific contact but provides no explicit guidance on when to use this tool versus alternatives like update_contact or get_contact_details. It does not mention exclusions, prerequisites, or when deletion might be inappropriate. The instruction 'Delete a specific contact' gives basic context but lacks comparative guidance.

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

• get_contact_detailsA
  3.9/5.0
  Behavior3/5

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

  With no annotations, the description must carry the full burden of behavioral disclosure. It specifies the input (contact_id UUID) and output (dict), but does not mention error handling, authentication, or confirm that the operation is read-only. The simple 'get' name suggests safety, but the description itself adds limited behavioral context beyond input/output.

  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 front-loaded with the primary purpose. The Args/Returns structure is clean and free of redundant information, though it could be slightly tighter by removing the placeholder 'Dict:' label.

  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 one-parameter get operation, this description adequately covers purpose, parameter, and return type. However, without an output schema, the return type 'A dictionary containing the contact details' is vague and could benefit from listing expected fields or mentioning potential error conditions. Still, the tool's simplicity makes the description sufficient.

  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 lists contact_id with type string, while the description adds that it must be a UUID, which is essential semantic meaning. This goes beyond the schema and clarifies the expected value format, justifying a strong score for a single parameter.

  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 retrieves details for a single contact using a UUID, which distinguishes it from sibling tools like get_contacts (list), create_contact, update_contact, and delete_contact. The verb 'Get details' and the specific resource ('specific contact') make the purpose unambiguous.

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

  Usage Guidelines3/5

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

  The description implies use for retrieving a specific contact's details, but it does not explicitly mention alternatives (e.g., get_contacts for listing) or when-not-to-use situations. No exclusions or comparisons to siblings are provided, so guidance is implicit rather than explicit.

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

• get_departmentsA
  3.9/5.0
  Behavior3/5

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

  With no annotations, the description carries the burden of disclosing behavior. It indicates a read-only action ('Get all departments') and specifies the return type (Dict), but does not mention potential errors, permissions, or other behavioral details. This is adequate for a simple list tool 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.

  Conciseness4/5

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

  The description is concise and front-loaded, with the main purpose in the first sentence. The additional context about departments and the return type are useful, but the 'Returns' section is slightly redundant with the description and could be more concise.

  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 zero-parameter tool with no output schema, the description is sufficiently complete. It explains what the tool does, the nature of departments, and the return type. Missing details like error handling are not critical for this simple read operation.

  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 schema coverage is high and description does not need to explain parameters. Per the baseline rule for 0 params, a score of 4 is appropriate.

  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 retrieves all departments from Tidio, with a specific verb and resource. It also differentiates departments as agent groups that can be assigned to tickets, distinguishing it from sibling tools like get_operators.

  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 context that departments are agent groups assignable to tickets, which implies when this tool would be useful. However, it does not explicitly state when to use this tool vs alternatives or provide exclusions.

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

• get_ticket_detailsA
  3.9/5.0
  Behavior3/5

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

  No annotations are provided, so the description carries the full burden. It discloses that the tool returns a dict with ticket details and includes messages, but doesn't mention access requirements, side effects, or error behavior. For a simple read operation, this is adequate but not comprehensive.

  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 purpose statement, then Args and Returns sections. Every sentence adds value with no filler.

  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 one-parameter read tool with no output schema, the description adequately explains what it does and what it returns. It doesn't cover error conditions, but that's not essential for this level of 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 description includes an Args section explaining ticket_id as the required ID of the ticket to retrieve, adding semantic meaning beyond the schema's bare integer type. This compensates for the 0% schema description coverage.

  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 retrieves a specific ticket's details from Tidio, including messages. It distinguishes itself from list tools like get_tickets by emphasizing 'specific ticket', though it doesn't explicitly name alternatives.

  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 context: use this when you need full ticket information including messages. It doesn't discuss when not to use it or mention sibling alternatives, which prevents a score of 5.

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

• create_ticketA
  4.2/5.0
  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 disclosure. It mentions that the assigned_department_id defaults to the 'General department' when not provided and states the return value (created ticket ID). However, it does not disclose potential side effects (e.g., auto-creating a contact), permissions required, or error behavior, leaving some transparency gaps 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-structured with a clear purpose statement, an Args section that mirrors the schema, and a Returns section. It is appropriately sized for 4 parameters, with no unnecessary fluff, though slightly longer than minimal due to the parameter explanations.

  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 (4 params, 3 required, no output schema, no annotations), the description provides all critical information: parameter meanings, defaults, and the return type. It could be improved by mentioning error handling or side effects, but for a create operation, it covers the essential context sufficiently.

  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%, and the description fully compensates by explaining each parameter: contact_email, subject, message_content are required, and assigned_department_id is optional with a UUID type and default behavior. It adds essential meaning beyond the schema's type/title fields.

  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 specific action: 'Create a new ticket in Tidio' and adds context that it creates from a customer's perspective. This distinguishes it from sibling tools like get_tickets, update_ticket, and delete_ticket.

  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 it (when a new ticket needs to be created) and provides context about the customer perspective. It doesn't explicitly mention alternatives or when not to use, but given that this is the only create-ticket tool among siblings, the usage context is clear enough.

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

• add_internal_note_to_a_ticketA
  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 full burden. It discloses the visibility of the note, the plain-text requirement for content, and the potential ValueError for invalid arguments. It also mentions the return value structure. This is solid transparency for a simple create-like operation, though it does not cover authorization or rate limits.

  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 Args, Returns, and Raises sections. It is appropriately sized and each section earns its place. The Args section adds value with additional constraints beyond the schema, and the Returns/Raises sections provide essential invocation details.

  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 no output schema, the description includes return and error behavior, making it complete for invocation. It also clarifies the internal visibility distinction. Minor gaps include lack of explicit prerequisites or prerequisites for operator_id, but overall it is sufficiently complete for the tool's simplicity.

  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 0%, the description adds meaning to parameters: ticket_id is 'the ID of the ticket', content 'must be plain text', and operator_id is 'the UUID of the operator'. This goes beyond the schema's bare types and titles, providing useful constraints and 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 the tool's purpose: adding an internal note to a specific ticket. It specifies the visibility (operators only, not sent to customer), which distinguishes it from sibling tools like 'reply_to_a_ticket'.

  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 context on when to use this tool by clarifying that the note is internal-only and not customer-facing. This implies it should be used instead of reply_to_a_ticket when the message is not meant for the customer. It does not explicitly name alternatives, but the context is clear.

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

• update_ticketA
  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 transparency burden. It discloses that the call returns a success dictionary and raises ValueError for invalid arguments, which is helpful. However, it does not mention permissions, reversibility, or whether omitted arguments leave fields unchanged, leaving important side-effect details unstated.

  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 opens with a crisp purpose sentence, then uses well-organized Args, Returns, and Raises sections. Every line provides necessary detail, particularly for the nested assigned object, without redundant fluff.

  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 a nested parameter and no output schema, the description thoroughly covers parameter semantics, return type, and error handling. It is slightly incomplete in not addressing usage context or side-effect transparency, but it is sufficient for invoking the tool correctly.

  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 provides no descriptions and no enums, but the description fully documents each parameter, including allowed status and priority values, the exact structure for assigned with an example, and required vs optional. This goes far beyond the schema and is essential for correct invocation.

  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 'Update a specific ticket from Tidio with new information', using a specific verb and resource that distinguishes it from create, delete, and get ticket tools. The title reinforces the same purpose without ambiguity.

  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 makes the tool's core use case clear—updating an existing ticket. However, it does not explicitly mention alternatives or exclusions, such as using unassign_ticket for removing assignments or reply_to_a_ticket for messaging, which would fully guide tool selection among siblings.

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

• get_contact_propertiesA
  4.4/5.0
  Behavior4/5

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

  With no annotations provided, the description carries the full burden of behavioral disclosure. It explains pagination mechanics in detail (meta.cursor behavior), describes the return payload structure, and clarifies the cursor parameter's role. This is strong transparency for a read-only list endpoint, though it does not cover auth or error conditions.

  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 with paragraphs and labeled sections (Args, Returns). It includes all necessary information without redundancy or fluff. Every sentence contributes to understanding the tool's behavior, making it efficiently concise.

  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?

  The description is complete for a single-parameter list endpoint. It explains the purpose, pagination details, parameter usage, and return format. Since there is no output schema, the description compensates by describing the return dictionary and property fields, making it sufficient for an agent to use the tool correctly.

  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 only a cursor parameter with no description, but the tool description fully explains its purpose, source (meta.cursor from previous response), and how to use it for pagination. This adds significant meaning beyond the schema, compensating for the 0% schema description coverage.

  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 retrieves all contact properties from Tidio and explains what these properties are (fields like name, email, phone, and custom ones). This specific verb+resource combination distinguishes it from sibling tools like get_contacts and get_contact_details, which deal with contact records rather than the schema of properties.

  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 explains what the tool does but does not explicitly state when to use it versus alternatives. It implies the tool is for fetching available fields, but it does not explicitly exclude or compare to sibling tools. The usage context is clear but not directly contrasted with other tools.

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

• get_operatorsA
  4.4/5.0
  Behavior4/5

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

  With no annotations provided, the description discloses pagination behavior in detail: how to use meta.cursor to fetch next pages and that null indicates the end. It also states the return type. This provides meaningful behavioral context beyond the tool's simple name.

  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 appropriately sized, with a brief intro, a clear pagination explanation, and structured Args/Returns sections. Every sentence adds value 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?

  Given the tool's simplicity (one optional parameter, no output schema), the description covers the key details: what it returns, pagination mechanics, and parameter semantics. It does not neglect important aspects and is complete for an agent to use the tool correctly.

  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 only lists a cursor parameter with no description (0% coverage). The description fully explains the cursor's purpose and usage: 'Pagination cursor from previous response. Use the value from meta.cursor to fetch the next page of results.' This compensates for the missing schema documentation.

  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 'Get all operators from Tidio' and defines operators as agents that manage tickets, distinguishing this from sibling tools like get_contacts or get_tickets. It uses a specific verb and resource.

  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 context about operators being agents assigned to tickets, which implies when to use it, but it does not explicitly compare to alternatives or state when not to use it. It lacks direct usage guidance such as 'Use this when you need a list of operators' or exclusions.

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

• get_ticketsA
  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 thoroughly explains pagination behavior (cursor handling) and return format, which are key traits. It lacks auth requirements or rate limits, but for a read-only list tool, the disclosed details are substantial.

  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 clear sections (overview, pagination, args, returns) and stays focused. The opening sentences are slightly repetitive, but the overall length is efficient and scannable.

  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 (one optional parameter, no output schema), the description covers the crucial pagination contract and return type. It doesn't enumerate ticket fields, but that isn't necessary for correct invocation. It is complete enough for an agent to use.

  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 lists a single cursor parameter with no description. The description's Args section adds essential meaning by explaining it as a pagination cursor from the previous response, fully compensating for the 0% schema coverage.

  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 retrieves all tickets from Tidio, using a specific verb+resource combination. It distinguishes from sibling get_ticket_details, which targets a single ticket, making the all-tickets scope evident.

  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 phrase 'Use this to get tickets overview' provides a clear context for when to choose this tool. However, it does not explicitly mention alternatives or when not to use it, so it stops short of full exclusions.

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

• reply_to_a_ticketA
  4.4/5.0
  Behavior4/5

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

  With no annotations provided, the description carries the burden of disclosing behavior. It states the reply is public and customer-visible, and it mentions the return format (success status and message ID). It does not cover permissions or side effects like irreversible sending, but the core behavior is transparently described.

  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. The purpose is stated in the first sentence, and the Args/Returns sections are clearly formatted without any redundant information.

  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 3 required parameters and no output schema, the description covers the purpose, all parameter semantics, and return value. It doesn't elaborate on error conditions or edge cases, but it is sufficiently complete for this tool's 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 input schema has 0% description coverage, but the Args section compensates by defining all three parameters. It adds meaningful details such as 'Can be HTML' for content and 'UUID' for operator_id, which are absent from the schema.

  Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

  Purpose5/5

  Does the description clearly state what the tool does and how it differs from similar tools?

  The description states 'Send a public reply to a specific ticket in Tidio' – a specific verb and resource. The word 'public' distinguishes it from the sibling tool 'add_internal_note_to_a_ticket', making it clear which tool to use for customer-visible replies.

  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 context by noting the reply is visible to the customer and sent to them, which implies when to use this tool. However, it doesn't explicitly mention alternatives or exclusions, such as 'use add_internal_note_to_a_ticket for private notes', so it stops short of full usage guidance.

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

• get_contactsA
  4.5/5.0
  Behavior4/5

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

  No annotations are provided, so the description carries the full burden. It discloses pagination behavior (meta.cursor null means end of list) and the exact-match constraint on email filtering. Being a read operation, these details cover the main behavioral traits, though it stops short of mentioning auth or rate limits.

  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: an opening summary, a pagination explanation, and clear Args/Returns sections. Every sentence adds value without redundancy, making it effective and easy to scan.

  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 no output schema, the description explains the return type as a dictionary with contacts and pagination metadata, and covers pagination flow. It lacks a detailed shape of individual contacts, but for a list endpoint this is acceptable, especially with sibling get_contact_details likely providing detail.

  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?

  With schema description coverage at 0%, the description fully compensates by explaining both parameters in an Args section: cursor is the pagination token from the previous response, and email is a valid full email filter. This adds meaning beyond the bare schema.

  Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

  Purpose5/5

  Does the description clearly state what the tool does and how it differs from similar tools?

  The description clearly states the tool's function: 'Get all contacts from Tidio' and defines what contacts are. It distinguishes itself from siblings like get_contact_details by explicitly covering the full list rather than a single contact.

  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 usage context for pagination (cursor handling) and email filtering, including a note that email must be a full valid address with no wildcards. However, it does not explicitly mention when to prefer this over alternatives like get_contact_details.

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

• create_contactA
  4.7/5.0
  Behavior5/5

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

  With no annotations provided, the description carries the full burden of behavioral disclosure and does so excellently. It warns that distinct_id must be a real external identifier, instructs the agent to ask the user if missing, and explicitly states 'Do NOT invent one or copy it from any other field.' It also discloses the 'never overwrites' behavior, required field conditions, return value, and potential ValueError, covering safety and error semantics thoroughly.

  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?

  Despite the length, the description is well-structured with Args, Returns, and Raises sections and front-loads the most critical facts (purpose, overwrite behavior, required field constraint, and the ask-if-missing rule). Each sentence adds value, such as parameter constraints and warnings, with no redundancy or fluff.

  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 is exceptionally complete for a no-annotation, no-output-schema tool, covering usage, parameters, return value, and errors. The only notable gap is that it does not specify what happens if a contact with the same distinct_id already exists—whether it creates a duplicate or fails. This missing behavior is relevant given the tool's emphasis on creating new contacts.

  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 provides zero descriptions (0% coverage), so the description must fully compensate—and it does. For every parameter, it adds meaning beyond type/name: distinct_id gets length limit and provenance rules, email gets RFC822 format, email_consent gets enum values, and properties gets item structure and a concrete example. This transforms ambiguous schema fields into actionable guidance.

  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 purpose: 'Create a new contact in Tidio.' It distinguishes itself from siblings by emphasizing 'Always creates a new contact; existing data is never overwritten,' which differentiates it from update_contact and delete_contact. The verb 'create' and resource 'contact' are specific 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 Guidelines4/5

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

  The description provides strong context for usage, specifying that a new contact is always created and never overwrites existing data, which implies it is for new contacts only. It also gives a clear constraint ('At least one of email, first_name, last_name, or phone must be provided') and the requirement for distinct_id. However, it does not explicitly name alternatives like update_contact for existing contacts, relying on sibling names and implication instead.

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

• update_contactA
  4.8/5.0
  Behavior5/5

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

  With no annotations, the description fully carries the behavioral burden. It reveals that omitted fields remain unchanged, null clears fields, distinct_id cannot be cleared, and it raises ValueError on invalid arguments. It also states the return type.

  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 uses a clear Args/Returns/Raises structure, front-loads the most important semantics, and every sentence adds value. It is detailed but not verbose.

  Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

  Completeness5/5

  Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

  Given the tool's complexity (8 parameters, mixed null semantics, special rules), the description is complete. It covers parameter constraints, return values, error behavior, and examples, and no output schema or annotations exist to fill gaps.

  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 compensate, and it does thoroughly. Every parameter is documented with format, constraints, and examples (e.g., email RFC822, distinct_id max 55 chars, properties 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 clearly states 'Update a specific contact in Tidio' with a specific verb and resource. It distinguishes itself from sibling tools like create_contact and delete_contact by focusing on updating an existing contact.

  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?

  It provides clear usage context: 'Pass only the fields you want to update' and explains omission/null behavior. However, it does not explicitly mention when not to use it or name alternative tools, 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.