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., "@Flightdeck MCP Server list my projects"
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.
A Model Context Protocol server that gives AI clients (Claude Code/Desktop, Cursor, …) first-class access to a Flightdeck instance — listing and creating projects, work items, cycles, modules and comments.
It's a thin client over Flightdeck's public REST API (/api/v1): it speaks
MCP over stdio to the AI client and HTTPS to your Flightdeck install, using a
personal access token. It never touches the app internals — the public API is
its entire surface.
Node.js ≥ 18
A Flightdeck install with the public API enabled (FD-21+)
A personal access token: in Flightdeck, go to Settings → API tokens,
create one, and copy the fd_pat_… value (shown only once). The token is
scoped to a single workspace and acts as you.
Related MCP server: Webvizio MCP Server
Two environment variables:
Variable | Required | Example |
| yes |
|
| yes |
|
claude mcp add flightdeck \
--env FLIGHTDECK_BASE_URL=https://flightdeck.example.com \
--env FLIGHTDECK_API_TOKEN=fd_pat_xxxxxxxx \
-- npx -y @cruglobal/flightdeck-mcp-serverAdd to your MCP config (claude_desktop_config.json or .cursor/mcp.json):
{
"mcpServers": {
"flightdeck": {
"command": "npx",
"args": ["-y", "@cruglobal/flightdeck-mcp-server"],
"env": {
"FLIGHTDECK_BASE_URL": "https://flightdeck.example.com",
"FLIGHTDECK_API_TOKEN": "fd_pat_xxxxxxxx"
}
}
}
}Tool | Description |
| Who/what the token maps to (user, workspace, token). Health check. |
| List projects in the workspace. |
| Retrieve a project by id. |
| List a project's work items (summary shape). |
| Retrieve a work item by id (full shape). |
| Create a work item in a project ( |
| Update a work item; only supplied fields change. |
| Delete a work item by id. |
| List a project's cycles. |
| Retrieve a cycle by id. |
| List a project's modules. |
| Retrieve a module by id. |
| List a work item's comments. |
| Add a comment to a work item. |
List tools accept page and per_page (max 100).
Writes are tenant-safe on the server: any referenced state, cycle, parent or label must belong to the work item's own project, and assignees must be members of the workspace — otherwise the API rejects the request.
npm install
npm run build # compile TypeScript to dist/
npm run watch # recompile on change
FLIGHTDECK_BASE_URL=… FLIGHTDECK_API_TOKEN=… npm startMIT
Add a comment to a work item.
| Name | Required | Description | Default |
|---|---|---|---|
| work_item_id | Yes | Work item id | |
| body | Yes | Comment text |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, and the description does not disclose behavioral traits such as whether comments are editable, deletion implications, or permission requirements. The description carries the full burden but offers only the action itself.
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 a single concise sentence with no unnecessary words. It is front-loaded and to the point, earning its place without waste.
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 2 parameters and no output schema, the description is minimally adequate. However, it lacks context about return values, side effects, or expected behavior (e.g., whether the comment is immediately visible).
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 100%, with both parameters (work_item_id, body) described in the schema. The description adds no additional meaning beyond what the schema already provides, so a baseline of 3 is appropriate.
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 'Add a comment to a work item' uses a specific verb ('Add') and resource ('comment to a work item'), clearly distinguishing it from sibling tools like 'list_comments' (lists) and 'create_work_item' (creates a work item).
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 you want to create a comment on a work item) but does not provide any explicit guidance on when not to use it, prerequisites, or alternatives. For example, it does not mention that 'list_comments' might be used to view existing comments.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Create a work item in a project. title is required; all other fields optional. Related ids (state/cycle/parent/label) must belong to the same project; assignees must be workspace members.
| Name | Required | Description | Default |
|---|---|---|---|
| project_id | Yes | Project id to create the item in | |
| title | Yes | Work item title (required) | |
| description | No | Plain-text description (empty string clears it) | |
| priority | No | Priority of the work item | |
| state_id | No | State id — must belong to the item's project | |
| parent_id | No | Parent work item id — same project | |
| cycle_id | No | Cycle id (same project), or null to remove the item from its cycle | |
| assignee_ids | No | User ids to assign; must be members of the workspace | |
| label_ids | No | Label ids to apply; must belong to the item's project | |
| start_date | No | ISO 8601 date (YYYY-MM-DD), or null to clear | |
| target_date | No | ISO 8601 date (YYYY-MM-DD), or null to clear | |
| estimate_point | No | Estimate points, or null to clear | |
| draft | No | Whether the item is a draft |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries full burden. It discloses constraints on id relationships but does not mention idempotency, error behavior, response format, authentication needs, or rate limits. For a creation tool, these are notable 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?
Two sentences, front-loaded with the primary action and then constraints. No wasted words.
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?
Given 13 parameters, no output schema, and no annotations, the description is sparse. It covers the core action and constraints, but omits what the tool returns, which is critical for an agent to use the result. However, the schema provides full parameter details.
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 100%, so baseline is 3. The description adds a brief overview reinforcing constraints already in schema, but does not provide new semantics beyond what is already documented per parameter.
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 'Create' and the resource 'work item in a project'. It distinguishes from sibling tools like update_work_item and delete_work_item. It explicitly notes that 'title' is required and other fields are optional.
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 clear constraints: related ids must belong to the same project, assignees must be workspace members. It implies when to use this tool (for creating work items) but does not explicitly state when not to use or list alternatives, though siblings are provided.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Permanently delete a work item by id.
| Name | Required | Description | Default |
|---|---|---|---|
| work_item_id | Yes | Work item id |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The description mentions 'permanently delete,' hinting at irreversibility, but it does not disclose other behaviors like cascading deletions, permission requirements, or side effects. With no annotations, the description carries the full burden, and it falls short.
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 a single sentence that efficiently conveys the core functionality with no extraneous words.
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?
Given the low complexity (1 parameter, no output schema), the description is minimally adequate. However, for a destructive operation, more context about consequences and required permissions would improve completeness.
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 coverage is 100%, and the description adds 'by id,' which aligns with the parameter. However, it does not add significant meaning beyond the input schema's parameter 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?
The description 'Permanently delete a work item by id' clearly states the action (delete) and the resource (work item), and it distinguishes from sibling tools like update_work_item or create_work_item.
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 provided on when to use this tool versus alternatives, such as update_work_item for reversible changes. No prerequisites or caution about irreversibility are mentioned.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Retrieve one cycle by id (includes progress_percent).
| Name | Required | Description | Default |
|---|---|---|---|
| cycle_id | Yes | Cycle id |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description must fully convey behavioral traits. It only states the core retrieval action and mentions a returned field, but does not disclose idempotency, error behavior, or any side effects. A read-only hint is lacking.
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?
A single, compact sentence of 10 words that conveys the essential purpose. No redundant or extraneous information.
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 one parameter and no output schema, the description provides sufficient information for an agent to invoke it correctly: it retrieves one cycle by id and includes progress_percent.
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 input schema already documents the single parameter 'cycle_id' with a description. The tool description adds no additional parameter-level meaning beyond what the schema provides. Schema coverage is 100%, so baseline 3 applies.
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 ('Retrieve') and the resource ('one cycle by id'), with an extra detail ('includes progress_percent'). It effectively distinguishes from siblings like list_cycles, which would return multiple cycles.
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 specific cycle_id is known, but does not explicitly state when to prefer this over alternatives like list_cycles. No exclusions or prerequisites are mentioned, which is acceptable for a simple retrieval tool but leaves room for improvement.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Return the user, workspace and token behind the configured Flightdeck API token. Useful as a connectivity/health check.
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries full burden. It discloses the return value (user, workspace, token) and a primary use case (health check). It does not mention side effects, but it's a simple read-only operation with no destructive hints needed.
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 two sentences, each earning its place: the first states what it returns, the second gives a concrete use case. No unnecessary words.
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?
Given zero parameters, no output schema, and a simple purpose, the description is fully complete. It tells the agent exactly what to expect and when to use it.
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 tool has zero parameters, and schema coverage is 100%. The description does not need to add parameter details, but it correctly implies no input is required. Baseline score for 0 parameters is 4.
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 it returns user, workspace, and token information using a specific verb 'Return'. It distinguishes itself from sibling tools like get_work_item or list_projects by focusing on identity and connectivity.
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 explicitly suggests use as a connectivity/health check, providing clear context. However, it does not mention when not to use it, though no alternative sibling tools perform the same function.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Retrieve one module by id (includes progress_percent).
| Name | Required | Description | Default |
|---|---|---|---|
| module_id | Yes | Module id |
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 only states what is returned, with no mention of side effects, permissions, or safety. As a retrieval operation, it likely has no side effects, but this is not explicitly stated.
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?
A single sentence of 9 words, front-loaded with the purpose. Every word is necessary, no redundancy. Perfectly concise for a simple tool.
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 retrieval with one parameter and no output schema, the description is adequate. It covers what the tool does and a key output field. However, it could hint at the output structure or mention that it returns the full module object.
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 already describes the parameter thoroughly (module_id with type and description). The description adds nothing about the parameter beyond what the schema provides. With 100% coverage, baseline 3 is appropriate.
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 'Retrieve one module by id', which is a specific verb+resource combination. It distinguishes from the sibling 'list_modules' by specifying a single retrieval, and adds value by noting that progress_percent is included.
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 context is implied (use when you need a single module by id), but there is no explicit guidance on when not to use it or alternatives like 'list_modules'. No exclusions or prerequisites mentioned.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Retrieve a single project by its id.
| Name | Required | Description | Default |
|---|---|---|---|
| project_id | Yes | Project id |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description must carry the full burden. It states the tool retrieves a single project, but provides no details on error handling (e.g., what happens if the id is invalid) or any other behavioral traits. While sufficient for a simple read operation, additional context like 'returns null if not found' would improve 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 at one sentence and 8 words, with no wasted information. It is front-loaded with the key action and resource.
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?
Given the tool's simplicity (1 parameter, no output schema, no nested objects), the description is largely complete. It clearly explains what the tool does, though it could mention that it returns the full project object. For a basic get operation, it 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?
Schema description coverage is 100% for the single parameter 'project_id'. The description adds 'by its id', which reinforces the schema but doesn't add new meaning. Baseline of 3 is appropriate since the schema already provides adequate parameter documentation.
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 'Retrieve', the resource 'project', and the method 'by its id'. It effectively distinguishes from sibling tools like list_projects (multiple projects) and get_cycle/get_module (different resources).
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 you have a project id. It doesn't explicitly state when not to use it, but the context of sibling tools (e.g., list_projects) provides natural differentiation. No alternative tools are named, but the purpose is clear enough.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Retrieve one work item by id (full shape: description + assignees, labels, parent, cycle).
| Name | Required | Description | Default |
|---|---|---|---|
| work_item_id | Yes | Work item id |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Discloses the full shape of the returned work item (description, assignees, labels, parent, cycle). No annotations exist, so it carries the burden well, though no mention of error handling or auth.
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?
Single sentence (17 words) with a parenthetical list. Front-loaded and efficient with no wasted words.
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?
Covers the primary purpose and return shape for a simple retrieval tool. Lacks error details but is sufficient given the tool's simplicity and sibling context.
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 already describes work_item_id as 'Work item id' with 100% coverage. Description adds minimal value beyond confirming id usage, so baseline 3 is appropriate.
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?
Clearly states the verb 'retrieve', resource 'work item', and scope 'by id'. The parenthetical list defines what 'full shape' includes, distinguishing it from list tools.
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?
Implies usage for single-item retrieval by id but lacks explicit guidance on when not to use or alternatives like list_work_items.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
List the comments on a work item, oldest first. Paginated.
| Name | Required | Description | Default |
|---|---|---|---|
| work_item_id | Yes | Work item id | |
| page | No | 1-based page number (default 1) | |
| per_page | No | Results per page, max 100 (default 50) |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations provided, so description carries full burden. Discloses ordering ('oldest first') and pagination behavior, which are key traits. Does not mention error handling or scope of comments, but sufficient for a read-only list tool.
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?
Two concise sentences, front-loaded with the main action. No filler or redundancy.
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?
Adequately covers key aspects: what the tool does, ordering, pagination. No output schema, but return type is implied. Could add error scenarios or field details, but not critical for a paginated list tool.
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 coverage is 100%, with each parameter described. The description adds no new parameter meaning beyond the schema, so baseline 3 is appropriate.
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?
Clear verb 'List' with specific resource 'comments on a work item'. Distinguishes from sibling tools like create_comment (write) or list_work_items (different resource). Also specifies ordering 'oldest first' and pagination.
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 when-to-use or when-not-to-use guidance. Usage is implied by the name and description, but lacks contrast with alternatives like list_work_items or get_work_item.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
List the cycles (sprints) of a project. Paginated.
| Name | Required | Description | Default |
|---|---|---|---|
| project_id | Yes | Project id | |
| page | No | 1-based page number (default 1) | |
| per_page | No | Results per page, max 100 (default 50) |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description must carry the full burden. It discloses listing and pagination but omits details like response structure, ordering, or permissions, which are important for a mutation-free tool.
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?
Two sentences, front-loaded with purpose, no wasted words. Efficient and clear.
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 list tool with no output schema, the description covers the basic behavior but lacks information about the return format (e.g., an array of cycle objects). Adequate but not 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?
Schema coverage is 100%, so baseline is 3. The description adds minimal value by clarifying cycles are 'sprints', but does not enhance parameter understanding beyond 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 the tool lists cycles (sprints) of a project and mentions pagination, distinguishing it from siblings like get_cycle (single cycle) and other list tools.
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 getting all cycles of a project, but does not explicitly compare with siblings like get_cycle or provide when-not-to-use guidance.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
List the modules (feature groups) of a project. Paginated.
| Name | Required | Description | Default |
|---|---|---|---|
| project_id | Yes | Project id | |
| page | No | 1-based page number (default 1) | |
| per_page | No | Results per page, max 100 (default 50) |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries full responsibility. It discloses pagination but does not mention read-only nature, authentication, or side effects. The 'List' action is typically read-only but not explicitly stated.
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 consists of two very short sentences that convey core purpose and pagination. There is no redundancy or unnecessary information, making it highly efficient.
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?
While the description clearly states the resource and pagination, it lacks details about the return format. Since no output schema exists, the description would benefit from mentioning the structure of the response, e.g., 'Returns an array of module objects with id, name, etc.'
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 input schema has 100% coverage with descriptions for all parameters. The description does not add additional meaning beyond the schema, so a baseline score of 3 is appropriate.
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 'List' and the resource 'modules (feature groups) of a project'. It mentions pagination, which adds context. This distinguishes it from siblings like 'get_module' (single module) and other list tools by resource.
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 retrieving all modules of a project but does not explicitly specify when to use it versus alternatives like 'get_module'. No when-not or exclusion criteria are provided.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
List the projects in the token's workspace (paginated).
| Name | Required | Description | Default |
|---|---|---|---|
| page | No | 1-based page number (default 1) | |
| per_page | No | Results per page, max 100 (default 50) |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations provided, so description carries full burden. Discloses pagination and scope (token's workspace), but does not explain behavior like ordering, error handling, or empty results. 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.
Is the description appropriately sized, front-loaded, and free of redundancy?
Single sentence, no redundant information. Perfectly concise and front-loaded with key action and result.
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?
Given it's a list tool with pagination parameters and no output schema, description covers scope and pagination. However, missing details like return object shape or sorting order, which would be helpful for completeness.
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 100%, so baseline is 3. Description adds no extra meaning beyond schema. Page and per_page are already well-documented in schema with defaults and constraints.
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?
Clearly states 'List the projects in the token's workspace (paginated)', specifying verb (List), resource (projects), and pagination feature. Distinguishes from sibling tools like get_project which retrieves a single project.
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?
Implies usage for listing all projects, but no explicit guidance on when to use vs alternatives (e.g., get_project) or when not to use. No mention of when pagination is needed.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
List work items in a project (summary shape), ordered by sequence number. Paginated.
| Name | Required | Description | Default |
|---|---|---|---|
| project_id | Yes | Project id | |
| page | No | 1-based page number (default 1) | |
| per_page | No | Results per page, max 100 (default 50) |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations provided, so description carries full burden. It discloses pagination and ordering but does not state that the operation is read-only or idempotent, nor any permissions or rate limits. Adequate but not rich.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Two sentences that front-load the key purpose and constraints. No redundant words; every phrase earns its place.
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 list tool with no output schema, the description covers scope (project), shape (summary), ordering, and pagination. It is complete enough, though it could mention that it does not filter by user or status.
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 coverage is 100%, with each parameter already described. The description adds value by noting pagination behavior and ordering by sequence number, which are not in schema descriptions. Adds meaningful context beyond 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 the verb 'list', resource 'work items', and specifics like 'in a project (summary shape)', 'ordered by sequence number', and 'Paginated'. This differentiates from sibling tools like get_work_item (single item) or create_work_item.
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 on when to use this tool versus alternatives (e.g., list_comments, list_cycles). The description implies usage for paginated listing of work items, but does not mention exclusions or conditions.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Update a work item by id. Only the fields you pass are changed. Pass cycle_id: null to remove it from its cycle.
| Name | Required | Description | Default |
|---|---|---|---|
| work_item_id | Yes | Work item id | |
| title | No | Work item title | |
| description | No | Plain-text description (empty string clears it) | |
| priority | No | Priority of the work item | |
| state_id | No | State id — must belong to the item's project | |
| parent_id | No | Parent work item id — same project | |
| cycle_id | No | Cycle id (same project), or null to remove the item from its cycle | |
| assignee_ids | No | User ids to assign; must be members of the workspace | |
| label_ids | No | Label ids to apply; must belong to the item's project | |
| start_date | No | ISO 8601 date (YYYY-MM-DD), or null to clear | |
| target_date | No | ISO 8601 date (YYYY-MM-DD), or null to clear | |
| estimate_point | No | Estimate points, or null to clear | |
| draft | No | Whether the item is a draft |
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 mentions partial updates and the null cycle_id behavior, but omits details on permissions, error handling, side effects, or return values. For a mutation tool with many parameters, this is insufficient.
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?
Two sentences conveying essential information without any unnecessary words or repetition.
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?
With 13 parameters and no output schema, the description does not cover constraints like project membership for parent_id or error states. It is decent but leaves gaps in understanding the full behavior.
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 coverage is 100% with each parameter described. The description adds value by emphasizing the partial update principle and the null cycle_id trick, which are not captured in 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 the action ('update'), the resource ('work item'), and the key behavior ('only the fields you pass are changed'). It distinguishes from siblings like delete_work_item and create_work_item.
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 explains partial updates and how to remove from a cycle, providing clear context. However, it does not explicitly state prerequisites (e.g., work item must exist) or when not to use this tool.
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.
v0.1.0create_commentcreate_work_itemdelete_work_itemget_cycleget_meget_moduleget_projectget_work_itemlist_commentslist_cycleslist_moduleslist_projectslist_work_itemsupdate_work_itemScored across 14 tools
Every tool has a clearly distinct purpose: CRUD operations for different entities (work items, cycles, modules, projects, comments) are separated, with no overlapping functionality. The 'get_me' tool serves a unique health check role.
All tools follow a consistent verb_noun pattern in snake_case (e.g., create_work_item, list_comments, get_cycle), making it predictable and easy for an agent to understand the action and resource.
With 14 tools covering core project management entities (projects, work items, cycles, modules, comments), the count is well-scoped. Each tool earns its place, and the number is manageable without being excessive or insufficient.
The tool surface provides full CRUD for work items and listing/getting for other entities, but lacks update and delete operations for comments, and there is no search or filtering across work items. These minor gaps do not severely hinder common workflows.
Manage Loom projects, tasks, bugs, defects, clients and phases from AI assistants
Remote MCP for Kanban AI boards—manage projects, tasks, and comments from AI tools.
Task management for people and AI agents, with scoped OAuth access to issues, projects, and docs.
Task management for people and AI agents, with scoped OAuth access to issues, projects, and docs.
