swsd-mcp

swsd_list_incident_tasks

Read-onlyIdempotent

Lists sub-tasks for a specified incident, returning details like ID, name, state, assignee, and dates. Use to view task progress and manage incident workflows.

Instructions

List sub-tasks on a SWSD incident. Returns id, name, description, state ("New" / "In Progress" / "Completed"), completed boolean, position, assignee, due_at, created_at, updated_at. Use swsd_create_incident_task to add a sub-task and swsd_update_task_state to mark one complete. Sub-tasks also appear inline in swsd_get_incident detail_level: "long".

Input Schema

TableJSON Schema

Name	Required	Description	Default
`incident_id`	Yes	SWSD incident reference. Accepts either the internal id (>=7 digits, e.g. 180457930) or the human-facing number (<=6 digits, e.g. 60310). The handler auto-detects via digit count.

Output Schema

TableJSON Schema

Name	Required	Description	Default
`count`	Yes
`tasks`	Yes
`incident_id`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

First observedv2.1.0May 28, 2026

TDQS

A4.5/5.0

Behavior4/5

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

Annotations already establish read-only, idempotent, non-destructive behavior, so the description doesn't need to repeat that. It adds value beyond annotations by clarifying that the returned data is also available inline in a long incident detail response and by naming the exact state enums ('New' / 'In Progress' / 'Completed'). This helps the agent reason about the data's origin and overlap.

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?

Three sentences, each earning its place: one states the operation and result shape, one names related mutation tools, and one gives a lightweight alternative lookup path. It is front-loaded and free of unnecessary filler.

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?

For a simple read-only list operation with one well-documented parameter and annotations covering safety, there is nothing material missing. The output schema presumably defines the return shape, and the description supplies the only needed selection context. This is complete enough for a capable agent.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The input schema already covers the sole parameter incident_id completely, including the internal-id vs. human-facing-number distinction and auto-detection logic. The description adds no further parameter-level meaning, so baseline 3 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 opens with a specific verb and resource: 'List sub-tasks on a SWSD incident.' This clearly distinguishes it from list_incidents, list_incident_comments, and other sibling tools. The list of returned fields reinforces exactly what the tool produces, removing any ambiguity about scope.

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

Usage Guidelines5/5

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

The description gives explicit routing guidance: use swsd_create_incident_task to add a sub-task and swsd_update_task_state to change state. It also notes that sub-tasks appear inline in swsd_get_incident with detail_level: 'long', giving the agent a known alternative path for retrieving the same data.

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

Install Server