Skip to main content
Glama

Create Manual Test Run

create_manual_run

Create a manual test run for a project, choosing all test cases or scoping to specific cases and suites, with tags, notes, release linking, and environment details.

Instructions

Create a new manual test run. Requires write permission. selectionMode controls which test cases are included: "all" (default — every case in the project) or "selected" (use testCaseIds and/or suiteIds to scope). releaseId attaches the run to a release. note accepts rich HTML. IMPORTANT: tags must be a JSON array of strings here — e.g. ["smoke","regression"] — NOT the comma-separated form that list_manual_runs accepts as a filter.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "projectId": "<projectId>",
      "name": "<name>"
    },
    "name": "create_manual_run"
  }
}

Input Schema

NameRequiredDescriptionDefault
nameYesRun name
noteNoRich HTML note
tagsNoArray of tag strings, e.g. ["smoke","regression"]. NOT a comma-separated string.
linksNoArray of link objects.
stateNoWorkflow state (default "new"). Either canonical ("in_progress") or display ("In Progress") form — server normalizes to lowercase+underscored so UI colors render correctly.
forecastNoNumeric forecast/target for the run (model stores this as a number).
suiteIdsNoSuite IDs whose cases are included when selectionMode="selected"
projectIdYesProject ID
releaseIdNoAttach run to this release
attachmentsNoNot supported over MCP: any value is refused with a 400. Tell the user to upload files in the TestDino UI.
environmentNoEnvironment label, e.g. "Staging"
testCaseIdsNoCase IDs to include when selectionMode="selected"
linkedIssuesNoArray of linked-issue objects (use the same shape returned by list_manual_runs).
selectionModeNoDefault "all"
includeUnsortedNoAlso include cases with no suite when selectionMode="selected"

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed4 schema fields changedv2.2.3
    • changedInput schema / properties / attachments / description
      Previous value: -"Array of attachment objects or URLs. Suggestion: attaching files via the hosted MCP can be token-expensive (the base64 payload flows through the LLM context). For lower token usage, consider the TestDino UI or the local `testdino-mcp` npm package."New value: +"Not supported over MCP: any value is refused with a 400. Tell the user to upload files in the TestDino UI."
    • removedInput schema / properties / attachments / items
      Removed value: -{
      -  "additionalProperties": true,
      -  "properties": {
      -    "_id": {
      -      "type": "string"
      -    },
      -    "blobUrl": {
      -      "type": "string"
      -    },
      -    "containerName": {
      -      "type": "string"
      -    },
      -    "fileContent": {
      -      "type": "string"
      -    },
      -    "fileName": {
      -      "type": "string"
      -    },
      -    "fileSize": {
      -      "type": "number"
      -    },
      -    "mimeType": {
      -      "type": "string"
      -    },
      -    "originalFileName": {
      -      "type": "string"
      -    },
      -    "uploadedAt": {
      -      "type": "string"
      -    },
      -    "uploadedBy": {
      -      "type": "string"
      -    },
      -    "url": {
      -      "type": "string"
      -    }
      -  },
      -  "type": "object"
      -}
    • removedInput schema / properties / attachments / type
      Removed value: -"array"
    • addedInput schema / properties / links / maxItems
      Added value: +50
  2. Changed25 schema fields changedv2.2.0
    • addedInput schema / $schema
      Added value: +"http://json-schema.org/draft-07/schema#"
    • addedInput schema / additionalProperties
      Added value: +false
    • changedInput schema / properties / attachments / description
      Previous value: -"Array of attachment objects or URLs."New value: +"Array of attachment objects or URLs. Suggestion: attaching files via the hosted MCP can be token-expensive (the base64 payload flows through the LLM context). For lower token usage, consider the TestDino UI or the local `testdino-mcp` npm package."
    • addedInput schema / properties / attachments / items / additionalProperties
      Added value: +true
    • addedInput schema / properties / attachments / items / properties
      Added value: +{
      +  "_id": {
      +    "type": "string"
      +  },
      +  "blobUrl": {
      +    "type": "string"
      +  },
      +  "containerName": {
      +    "type": "string"
      +  },
      +  "fileContent": {
      +    "type": "string"
      +  },
      +  "fileName": {
      +    "type": "string"
      +  },
      +  "fileSize": {
      +    "type": "number"
      +  },
      +  "mimeType": {
      +    "type": "string"
      +  },
      +  "originalFileName": {
      +    "type": "string"
      +  },
      +  "uploadedAt": {
      +    "type": "string"
      +  },
      +  "uploadedBy": {
      +    "type": "string"
      +  },
      +  "url": {
      +    "type": "string"
      +  }
      +}
    • addedInput schema / properties / attachments / items / type
      Added value: +"object"
    • changedInput schema / properties / environment / description
      Previous value: -"Environment label, e.g. 'Staging'."New value: +"Environment label, e.g. \"Staging\""
    • addedInput schema / properties / forecast / description
      Added value: +"Numeric forecast/target for the run (model stores this as a number)."
    • addedInput schema / properties / forecast / type
      Added value: +"number"
    • addedInput schema / properties / includeUnsorted / description
      Added value: +"Also include cases with no suite when selectionMode=\"selected\""
    • changedInput schema / properties / linkedIssues / description
      Previous value: -"Array of linked-issue objects (same shape list_manual_runs returns)."New value: +"Array of linked-issue objects (use the same shape returned by list_manual_runs)."
    • addedInput schema / properties / linkedIssues / items / additionalProperties
      Added value: +true
    • addedInput schema / properties / linkedIssues / items / properties
      Added value: +{
      +  "displayId": {
      +    "type": "string"
      +  },
      +  "issueType": {
      +    "type": "string"
      +  },
      +  "source": {
      +    "type": "string"
      +  },
      +  "status": {
      +    "type": "string"
      +  },
      +  "title": {
      +    "type": "string"
      +  },
      +  "url": {
      +    "type": "string"
      +  }
      +}
    • addedInput schema / properties / linkedIssues / items / type
      Added value: +"object"
    • addedInput schema / properties / links / items / additionalProperties
      Added value: +true
    • addedInput schema / properties / links / items / properties
      Added value: +{
      +  "title": {
      +    "type": "string"
      +  },
      +  "url": {
      +    "type": "string"
      +  }
      +}
    • addedInput schema / properties / links / items / type
      Added value: +"object"
    • changedInput schema / properties / name / description
      Previous value: -"Run name (required)."New value: +"Run name"
    • changedInput schema / properties / note / description
      Previous value: -"Rich HTML note."New value: +"Rich HTML note"
    • changedInput schema / properties / projectId / description
      Previous value: -"Project ID (required)."New value: +"Project ID"
    • changedInput schema / properties / releaseId / description
      Previous value: -"Attach run to this release."New value: +"Attach run to this release"
    • changedInput schema / properties / selectionMode / description
      Previous value: -"Default 'all'."New value: +"Default \"all\""
    • changedInput schema / properties / state / description
      Previous value: -"Workflow state (default 'new'). Either canonical ('in_progress') or display ('In Progress') form — server normalizes to lowercase+underscored so UI colors render correctly."New value: +"Workflow state (default \"new\"). Either canonical (\"in_progress\") or display (\"In Progress\") form — server normalizes to lowercase+underscored so UI colors render correctly."
    • addedInput schema / properties / suiteIds / description
      Added value: +"Suite IDs whose cases are included when selectionMode=\"selected\""
    • addedInput schema / properties / testCaseIds / description
      Added value: +"Case IDs to include when selectionMode=\"selected\""
  3. Addedv1.0.10

TDQS

A4.3/5.0
Behavior4/5

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

Annotations already declare readOnlyHint=false, destructiveHint=false, openWorldHint=false, and nothing contradicts them ('create' matches a non-read-only, non-destructive write). The description adds value beyond annotations: the write-permission requirement, that note takes rich HTML, and the tags-format gotcha that differs from list_manual_runs.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

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

Front-loaded with purpose, then the key conditional parameters, then the IMPORTANT tags warning last where it's most visible. Slightly param-list-like but each clause earns its place; no filler.

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

Completeness4/5

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

For a 15-parameter creation tool with full schema coverage and no output schema, the description covers the only tricky interactions (selectionMode + testCaseIds/suiteIds, tags format) and the permission prerequisite. It leaves the long tail of params to the schema, which is appropriate.

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 100%, so the baseline is 3, but the description earns above it: it explains selectionMode semantics end-to-end and flags the critical JSON-array-vs-comma-separated tags distinction that mirrors a sibling's filter format. It doesn't cover the remaining params (state, forecast, links, linkedIssues) but the schema already documents those.

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?

States a specific verb ('Create') plus resource ('manual test run') immediately, and 'new' separates it from update_manual_run. An agent can tell what it produces without opening the schema.

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

Usage Guidelines4/5

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

Explains the selectionMode branches (all vs. selected with testCaseIds/suiteIds) and the write-permission prerequisite, which is real usage context. It doesn't explicitly say when to prefer a sibling like create_manual_test_case or when not to use this tool, so it stops short of a 5.

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