Allows sending emails via Gmail as part of employee onboarding workflow.
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@HR-ASSIST Onboard Alice, Software Developer, start date 2025-04-01"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
HR ASSIST is an Agentic AI system designed to help HR teams automate routine workflows. This example demonstrates automation of the employee onboarding process, streamlining tasks that typically require manual intervention.
In terms of technical architecture, for MCP client we use Claude Desktop and the code base here represents the MCP server with necessary tools that will be used by MCP client
🛠️ Setup Instructions
To set up and run HR ASSIST, follow these steps:
Configure claude_desktop_config.json Add the following configuration to your claude_desktop_config.json file:
{
"mcpServers": {
"hr-assist": {
"command": "C:\\Users\\dhanush\\.local\\bin\\uv",
"args": [
"--directory",
"C::\\code\\atliq-hr-assist",
"run",
"server.py"
],
"env": {
"CB_EMAIL": "YOUR_EMAIL",
"CB_EMAIL_PWD": "YOUR_APP_PASSWORD"
}
}
}
}Replace YOUR_EMAIL with your actual email.
Replace YOUR_APP_PASSWORD with your email provider’s app-specific password (e.g., for Gmail).
Run uv init and uv add mcp[cli] as per the video tutorial in the course.
Usage
Click on the + icon and select the Add from hr-assist option, and send the request.
Fill the details for the new employee:
Alternatively, you can draft a custom prompt and let the agent take over.
Add a new employee to the HRMS system. :param emp_name: Employee name :param manager_id: Manager ID (optional) :return: Confirmation message
| Name | Required | Description | Default |
|---|---|---|---|
| Yes | |||
| emp_name | Yes | ||
| manager_id | Yes |
| Name | Required | Description |
|---|---|---|
| result | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries the full burden. It does mention a confirmation message as the return value, but it fails to disclose side effects, permissions, or validation behavior. More critically, it contradicts the input schema by labeling manager_id as optional when the schema requires it, which is misleading.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is concise and front-loaded with the core action. The :param/:return format is somewhat archaic but not verbose. However, structure is hampered by missing email documentation and the optionality error, which reduce overall clarity.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a simple create operation, the description provides a basic purpose and return value, but it is incomplete: it omits the email parameter, contradicts the schema on manager_id, and offers no context about validity, permissions, or when to use the tool. The output schema exists but is not referenced or explained.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
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 offers brief semantics for emp_name and manager_id, but incorrectly marks manager_id as optional and omits the email parameter entirely. This partial and inaccurate coverage does not reliably aid the agent in understanding required inputs.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the action 'Add a new employee to the HRMS system,' which is specific and identifies the resource. However, it does not explicitly differentiate from sibling tools like get_employee_details or apply_leave, and the optionality of manager_id introduces ambiguity about actual inputs.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
There is no guidance on when to use this tool vs. alternatives. The description lacks any context about prerequisites, appropriate scenarios, or when other employee-related tools should be used instead.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Apply for leave for an employee. :param emp_id: Employee ID :param leave_dates: List of leave dates :return: Leave application status message
| Name | Required | Description | Default |
|---|---|---|---|
| emp_id | Yes | ||
| leave_dates | Yes |
| Name | Required | Description |
|---|---|---|
| result | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description alone must disclose behavioral traits. It only states the action and return value, without mentioning whether the operation checks leave balance, requires permissions, is reversible, or triggers notifications. For a mutation tool, this lacks necessary behavioral transparency.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is extremely concise, front-loading the purpose in the first sentence and adding param documentation without any fluff. Every sentence earns its place, and the structure is clear and scannable.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a simple tool with two parameters and an output schema, the description covers purpose, parameters, and return value adequately. However, it lacks context about practical usage, such as prerequisites (e.g., sufficient leave balance) or side effects, but given the tool's simplicity and existing output schema, this is acceptable.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The description provides :param lines for both parameters, adding semantics to the otherwise empty schema descriptions. 'Employee ID' and 'List of leave dates' clarify the parameters' meanings, though the format of dates (e.g., date range vs individual dates) is not specified. This partly compensates for the 0% schema coverage.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description states 'Apply for leave for an employee' clearly, specifying the verb (apply) and resource (leave) with a target (employee). It is unambiguous and distinct from all sibling tools, including leave balance and history queries, which serve different purposes.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
Usage is implied from the purpose: this is the tool to apply for leave. However, no explicit guidance is given about when to use it versus checking leave balance first or any approval workflow. Alternatives are not mentioned, and no exclusions are provided.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Cancel a scheduled meeting for an employee. :param employee_id: Employee ID :param meeting_datetime: Date and time of the meeting in python datetime format :param topic: Topic of the meeting (optional) :return: Confirmation message
| Name | Required | Description | Default |
|---|---|---|---|
| topic | No | ||
| employee_id | Yes | ||
| meeting_datetime | Yes |
| Name | Required | Description |
|---|---|---|
| result | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description must disclose side effects and behavior. It only states the action and returns a 'Confirmation message,' but does not mention irreversibility, required permissions, or what happens if the meeting does not exist. This is minimal transparency for a mutation.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is compact and front-loaded with a single-sentence purpose, followed by a parameter list. Every line earns its place, with no filler or repetition of schema details.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
The description covers the core operation and parameter semantics, making it usable for a straightforward cancellation. However, it lacks behavioral context (side effects, prerequisites) and usage guidance, leaving gaps especially given the absence of annotations.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The description includes docstring-style explanations for all three parameters, clarifying employee_id, meeting_datetime format, and topic optionality. This adds significant meaning beyond the schema titles, especially since schema description coverage is 0%. Minor vagueness in 'python datetime format' prevents a 5.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description opens with a clear verb+resource statement: 'Cancel a scheduled meeting for an employee.' This unambiguously identifies the tool's function and distinguishes it from siblings like schedule_meeting and get_all_meetings_for_employee.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance is given on when to use this tool versus alternatives. The description does not mention when cancellation is appropriate, nor does it reference sibling tools or exclusions. Usage is left entirely to the agent's inference.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Create a ticket for buying required items for an employee. :param emp_id: Employee ID :param item: Item requested (Laptop, ID Card, etc.) :param reason: Reason for the request :return: Confirmation message
| Name | Required | Description | Default |
|---|---|---|---|
| item | Yes | ||
| emp_id | Yes | ||
| reason | Yes |
| Name | Required | Description |
|---|---|---|
| result | Yes |
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 only mentions creating a ticket and returning a confirmation message, but does not disclose side effects, permissions, reversibility, or any other behavioral traits. For a mutation operation, this is a significant gap.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
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 parameter documentation is clear and directly follows the purpose, with no unnecessary content. It efficiently conveys all essential information in four short statements.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a simple ticket-creation tool, the description covers the primary purpose, all parameters, and the return type (confirmation message). It also provides examples for the item field. However, it lacks mention of prerequisites (e.g., employee must exist) or error conditions, but the simplicity of the tool makes these omissions minor.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The schema has no descriptions for its parameters (0% coverage), so the description must compensate. It does so thoroughly by providing meanings for all three parameters: emp_id (Employee ID), item (Item requested with examples), and reason (Reason for the request). This fully clarifies the required inputs.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states 'Create a ticket for buying required items for an employee,' which uses a specific verb ('create') and resource ('ticket') with a clear purpose. This differentiates it from sibling tools like update_ticket_status and list_tickets, which handle other ticket operations.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description implies the use case (creating a ticket for employee purchases) but does not explicitly state when to use this tool versus alternatives. There are no exclusions or comparisons with sibling tools like list_tickets or update_ticket_status, so the 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.
Get the list of meetings scheduled for an employee. :param employee_id: Employee ID :return: List of meetings
| Name | Required | Description | Default |
|---|---|---|---|
| employee_id | Yes |
| Name | Required | Description |
|---|---|---|
| result | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries the full burden of disclosing behavioral traits. It only says 'Get the list of meetings' and returns a list, but does not mention whether this includes past/future meetings, canceled meetings, ordering, pagination, or any side effects. The behavior is presumed read-only but never explicitly stated, and no additional context beyond the basic action is provided.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is short and structured with a param/return docstring format. It contains only the essential information and is easy to scan. The ':param' and ':return' lines are somewhat redundant with the schema and tool name, but they don't add significant clutter.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a simple single-parameter read tool, the description is minimally viable. The output schema exists, so return values need not be detailed. However, the description omits important contextual details such as the scope of meetings (all time? upcoming only?), whether canceled meetings are included, and any filtering or sorting behavior. These are clear gaps given the sibling tools and potential ambiguity.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
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 adds a ':param employee_id: Employee ID' line, but this merely restates the schema's title 'Employee Id' and type 'string'. It doesn't specify the format, source (e.g., from get_employee_details), or any constraints (e.g., required, non-empty). The ':return: List of meetings' is generic. Thus the description provides minimal added meaning over the schema.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states 'Get the list of meetings scheduled for an employee' with a specific verb ('Get'), resource ('list of meetings'), and intended subject ('employee'). It is easily distinguished from sibling tools like schedule_meeting and cancel_meeting, which are write operations, while this is a read operation.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
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, such as when to use schedule_meeting or cancel_meeting, nor does it mention any prerequisites or exclusions. Usage is only implied by the tool's name and action ('Get list of meetings'), which is not sufficient for an agent to choose it confidently among siblings.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Get employee details by name. :param name: Name of the employee :return: Employee ID and manager ID
| Name | Required | Description | Default |
|---|---|---|---|
| name | Yes |
| Name | Required | Description |
|---|---|---|
| result | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description must convey behavioral traits. It clearly indicates a read-only 'Get' operation and exposes the return fields. However, it lacks details on matching behavior (e.g., exact vs. partial name, case sensitivity) and error handling when an employee is not found, leaving important gaps.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is concise and front-loads the main purpose. The param and return lines are clearly separated and add useful information without redundancy. It is slightly less polished than a purely declarative sentence but remains well-structured and free of filler.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
The tool is a simple lookup with one parameter and an output schema exists, so the description covers the essential request and response shape. However, it lacks usage guidance relative to sibling tools and does not address ambiguity or failure cases. Overall, it is minimally complete but has noticeable gaps.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The schema has no description for the 'name' parameter (0% coverage), so the description's ':param name: Name of the employee' adds minimal meaning beyond the parameter name itself. It does not specify format, case sensitivity, or matching semantics, so it fails to compensate 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.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states a specific verb and resource: 'Get employee details by name.' It also specifies the return values (Employee ID and manager ID), making the purpose unambiguous. This distinguishes it from the sibling tool get_employee_leave_balance, which focuses on leave data.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
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 such as get_employee_leave_balance or list_tickets. It does not mention exclusions, prerequisites, or preferred use cases. The only implied usage is from the verb 'Get,' which is not sufficient.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Get the leave balance of an employee. :param emp_id: Employee ID :return: Leave balance message
| Name | Required | Description | Default |
|---|---|---|---|
| emp_id | Yes |
| Name | Required | Description |
|---|---|---|
| result | Yes |
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 only states that the tool returns a 'leave balance message', which is vague and does not clarify side effects, error behavior, permission requirements, or whether the result is structured or plain text. The verb 'get' implies read-only, but the description does not explicitly confirm this or provide any additional behavioral context.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is highly concise and well-structured. It uses a single sentence to describe the action, followed by explicit :param and :return lines for the important contract points. There is no fluff, and the information is front-loaded in the opening sentence.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
The tool is simple, but the description has clear gaps: it does not explain when to use it over 'get_leave_history', does not describe the exact return format beyond 'message', and gives no behavioral details. Given the missing annotations and zero schema coverage, the description is minimally adequate but lacks the context needed for an agent to reliably distinguish and invoke this tool in all scenarios.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
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. The :param line clarifies that 'emp_id' stands for 'Employee ID', which adds slight meaning beyond the schema's property name and title. However, it does not specify the format or constraints for the ID, and it is nearly redundant with the parameter name. The compensation is minimal but present.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
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 the leave balance of an employee.' It uses a specific verb ('get') and resource ('leave balance') and distinguishes from siblings like 'get_leave_history' which covers historical records, not current balance. The :param and :return lines further clarify the tool's purpose.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
There is no guidance on when to use this tool versus alternatives like 'get_leave_history' or 'apply_leave'. The description does not mention prerequisites, exclusions, or any preference for which sibling to choose. The only context is the name and a basic description, leaving the agent to infer from the tool name alone.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Get the leave history of an employee.
Args: emp_id (str): the employee ID for whom the leave history is being requested
Returns: List[Dict[str, str]]: List of leave history entries
| Name | Required | Description | Default |
|---|---|---|---|
| emp_id | Yes |
| Name | Required | Description |
|---|---|---|
| result | Yes |
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 states that the tool returns a list of leave history entries but does not disclose behavior for invalid employee IDs, permission requirements, or potential errors. It is a simple read operation, but the description offers minimal transparency beyond the basic 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.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is compact and front-loaded with the main purpose, followed by structured Args and Returns sections. Every sentence adds value; there is no redundancy or filler.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a simple read-only tool with one parameter and an output schema (though not shown), the description is sufficiently complete. It states the return type as a list of dicts, which gives the caller a clear idea of the result shape. It doesn't cover edge cases, but for this complexity level, the description is adequate.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The description adds meaningful context for the only parameter, emp_id, by specifying it is the employee ID for whom leave history is requested. This goes beyond the schema, which only provides the type and title. No other parameters exist, so the description adequately covers the parameter's meaning.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the verb 'Get' and resource 'leave history of an employee', distinguishing it from related sibling tools like get_employee_leave_balance (which retrieves balance) and get_employee_details (which retrieves general employee info). 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.
Does the description explain when to use this tool, when not to, or what alternatives exist?
No explicit guidance is given on when to use this tool versus alternatives. The intended usage is implied by its name and description—use it when you need the full leave history of an employee—but it does not explicitly mention exclusions or compare with siblings such as get_employee_leave_balance or apply_leave.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
List tickets for an employee with optional status filter. :param employee_id: Employee ID (optional) :param status: Ticket status (optional) :return: List of tickets
| Name | Required | Description | Default |
|---|---|---|---|
| status | No | ||
| employee_id | No |
| Name | Required | Description |
|---|---|---|
| result | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the full burden. It states the action ('List tickets') and return type, but does not explicitly confirm read-only behavior, side effects, or how the optional parameters affect the result (e.g., whether omitting employee_id returns all tickets).
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is brief and front-loaded, with a single purpose sentence and concise parameter/return annotations. It avoids fluff, but is under-informative.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
The description leaves ambiguity about the optional parameters: it says 'for an employee' but employee_id is optional, and does not clarify what happens when filters are omitted. It also omits allowed status values. Despite having an output schema, the description is incomplete for a tool with optional filters.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The description provides only basic restatements of the parameter names ('Employee ID', 'Ticket status') and marks them optional, adding little meaning beyond the schema. It does not specify allowed status values or the behavior when omitted.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description uses a specific verb ('List') and resource ('tickets'), and adds scope ('for an employee') with an optional status filter, clearly distinguishing it from sibling tools like create_ticket and update_ticket_status.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description implies usage for reading tickets, and mentions the optional status filter, but does not explicitly state when to use this tool versus creating or updating tickets, nor any prerequisites or exclusions.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Schedule a meeting for an employee. :param employee_id: Employee ID :param meeting_datetime: Date and time of the meeting in python datetime format :param topic: Topic of the meeting :return: Confirmation message
| Name | Required | Description | Default |
|---|---|---|---|
| topic | Yes | ||
| employee_id | Yes | ||
| meeting_datetime | Yes |
| Name | Required | Description |
|---|---|---|
| result | Yes |
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 only states that a meeting is scheduled and a confirmation message is returned, but omits important details like conflict handling, validation of employee_id, timezone assumptions, or whether any notifications are sent. This could lead to misuse or unexpected side effects.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is concise and front-loaded with the main action, followed by a compact parameter list and return note. No wasted sentences; every element serves a purpose.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a simple tool with 3 required string parameters, the description covers the basic parameters and return type, but lacks critical behavioral context such as meeting conflict resolution, employee validation, and timezone handling. The presence of an output schema partially covers return details, but the absence of annotations and behavioral clarifications leaves gaps.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The description includes :param lines that explain each parameter, adding 'python datetime format' for meeting_datetime which is helpful. However, most explanations are redundant with property titles, and with 0% schema coverage, the description only partially compensates. It doesn't clarify constraints like required formats or uniqueness.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description 'Schedule a meeting for an employee' uses a specific verb and resource, clearly distinguishing it from sibling tools like 'cancel_meeting', 'get_meetings', and 'apply_leave'. No ambiguity about the tool's primary action.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The purpose statement gives clear context that this tool is for creating meetings, and the sibling tools provide implicit alternatives (cancel, view, etc.). It doesn't explicitly mention when not to use it or name alternatives, but the context is strong enough for an agent to select it appropriately.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
| Name | Required | Description | Default |
|---|---|---|---|
| body | Yes | ||
| html | No | ||
| subject | Yes | ||
| to_emails | Yes |
| Name | Required | Description |
|---|---|---|
| result | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Tool has no description.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Tool has no description.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Tool has no description.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Tool has no description.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
Tool has no description.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
Tool has no description.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Update the status of a ticket. :param ticket_id: Ticket ID :param status: New status (Open, In Progress, Closed)
| Name | Required | Description | Default |
|---|---|---|---|
| status | Yes | ||
| ticket_id | Yes |
| Name | Required | Description |
|---|---|---|
| result | Yes |
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 of behavioral disclosure. It states that the tool updates a status but does not mention whether this is a mutating operation with side effects, whether permissions are required, or what happens if the ticket ID is invalid. The description adds minimal behavioral context beyond the verb 'update'.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is extremely concise, consisting of a single clear purpose sentence and two parameter definitions. Every word earns its place, with no redundant or verbose content.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a simple two-parameter tool with an output schema, the description covers the core purpose and parameter meanings. However, it lacks details on when to use the tool (usage guidelines) and any behavioral side effects or constraints. The presence of an output schema reduces the need to explain return values, but the missing usage and behavioral context keeps it from being fully complete.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The schema has no descriptions, so the description must compensate. It does: it explains ticket_id as 'Ticket ID' and status as 'New status (Open, In Progress, Closed)', explicitly listing valid status values. This adds meaningful meaning beyond the raw schema properties.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the action ('Update the status') and the resource ('a ticket'), and includes parameter definitions for ticket_id and status. It is distinct from sibling tools like create_ticket and list_tickets, making its purpose unambiguous.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description implies usage when a ticket's status needs to be changed, but it does not provide explicit guidance on when to use this tool versus alternatives, nor does it mention any prerequisites or exclusions. The sibling tool names hint at context but are not referenced.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
v0.1.0add_employeeapply_leavecancel_meetingcreate_ticketget_all_meetings_for_employeeget_employee_detailsget_employee_leave_balanceget_leave_historylist_ticketsschedule_meetingsend_emailupdate_ticket_statusScored across 12 tools
Each tool targets a distinct resource/action: employee management, email, tickets, meetings, and leave. No two tools overlap in purpose, making selection unambiguous.
All tools follow a consistent verb_noun pattern in snake_case (add_employee, get_employee_details, create_ticket, schedule_meeting, etc.). No mixed conventions or chaotic naming.
With 12 tools covering multiple HR sub-domains (employee, ticket, meeting, leave, email), the count is well-scoped and appropriate for the server's purpose, neither too thin nor overwhelming.
Core workflows are covered: employee creation/retrieval, ticket lifecycle (create/update/list), meeting scheduling/cancellation/list, leave balance/apply/history. Minor gaps exist (e.g., no employee update/delete, no single ticket detail, no leave cancellation) but they are workable.
AI-powered corporate learning platform — manage courses, users, and insights via Claude.
Build and manage AI-native customer support agents from Claude or any MCP client.
Give AI agents 30,000+ safe, token-optimized actions across Workday, SAP, Oracle + hundreds more.
Build agents to automate any background task. Works with your ChatGPT/Claude subscription.
