testit-mcp-server

search_work_items

Read-only

Query and filter TestIT work items across projects by name, type, state, priority, tags, or custom fields to find test cases, checklists, and shared steps.

Instructions

Search work items across projects. Typed filter fields are combined with an optional raw "filter" object (TestIT WorkItemFilterApiModel) for advanced fields.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "search_work_items"
  }
}

Input Schema

Name	Required	Description
`name`	No	Filter by (part of) work item name.
`page`	No	1-based page number; alternative to skip. Uses "size" (default 50).
`size`	No	Page size for "page"; alias of take.
`skip`	No	Number of items to skip (offset).
`tags`	No	Tag names.
`take`	No	Max number of items to return.
`types`	No	Work item types.
`filter`	No	Raw WorkItemFilterApiModel fields (e.g. createdDate, attributes, autoTestIds).
`states`	No
`orderBy`	No	Sort expression, e.g. "createdDate desc".
`nameOrId`	No	Work item name part or global ID.
`globalIds`	No	Global numeric IDs.
`isDeleted`	No	Search archived (deleted) work items.
`priorities`	No
`projectIds`	No	Project UUIDs.
`sectionIds`	No	Section UUIDs.
`isAutomated`	No
`searchField`	No	Field name to search in.
`searchValue`	No	Value to search for in searchField.

Schema Changelog

Changes observed during successful MCP inspections.

First observedv0.2.0Nov 14, 2026

TDQS

B3.4/5.0

Behavior3/5

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

Annotations already establish readOnlyHint=true and openWorldHint=true, so safety is covered. The description adds that typed fields are combined with the optional raw filter object, which is useful behavioral context, but it says nothing about result caps, default ordering, or what happens with archived items (the isDeleted flag), and there is no output schema to fall back on.

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?

Two sentences, zero padding, with the core action front-loaded and the filter-composition rule immediately after. Nothing is repeated from the schema.

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

Completeness3/5

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

For a 19-parameter, zero-required, nested-object tool with no output schema, the description is thin: it omits paging/alias semantics among page, size, skip, and take, and does not describe the shape of results. The filter-composition sentence and high schema coverage keep it merely adequate rather than inadequate.

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

Parameters4/5

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

Schema coverage is 84%, so the baseline would be 3; the description earns above that by explaining the interplay between typed filter properties and the nested raw filter object, and by naming the underlying model (TestIT WorkItemFilterApiModel) so an agent knows what keys the free-form object accepts.

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

Purpose4/5

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

States a specific verb and resource plus scope: 'Search work items across projects.' An agent can tell it is a cross-project search, but the description never distinguishes it from the sibling list_work_items or explains the search/filter relationship.

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

Usage Guidelines2/5

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

No when-to-use guidance at all: nothing says when to prefer this over list_work_items, when to use typed fields vs the raw filter object, or how the four paging parameters (page/size/skip/take) should be chosen. The only implied guidance is that the raw filter is for 'advanced fields'.

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

Deploy Server