Skip to main content
Glama
MCP WorkBoard CrunchTools

MCP WorkBoard CrunchTools

by crunchtools

Workboard Create Objective Tool

workboard_create_objective_tool

Create Team or Individual objectives with owners, dates, and optional key results and targets. Use it to set up new OKRs in WorkBoard, since objectives cannot be updated or deleted later via API.

Instructions

Create a new objective with optional key results.

Creates Team or Individual objectives. The API has no update or delete for objectives — those are UI-only, so a name or date that is wrong at creation stays wrong until someone fixes it in the web UI.

This used to say Data-Admin was required and that instant JWT tokens cannot create objectives. That is wrong: an instant token carrying isSuperUser: false creates objectives and checks in progress against their key results. Data-Admin does gate other calls, scope="org" on workboard_list_users_tool among them, so do not generalise from that to every write; test the specific call instead of assuming either way.

Team objectives must be tied to a team: pass team (a team ID from workboard_get_teams_tool). Provide the objective name, owner, dates, and optionally key results with targets. Each key result has a name and optional start_value, target_value, and unit_type (e.g. "Number", "Currency", "Percent").

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": {
      "name": "<name>",
      "owner": "<owner>",
      "start_date": "<start_date>",
      "target_date": "<target_date>"
    },
    "name": "workboard_create_objective_tool"
  }
}

Input Schema

NameRequiredDescriptionDefault
nameYesObjective name (e.g. "Increase customer retention")
teamNoTeam ID (or name) — required for team objectives, ignored for individual
ownerYesOwner's email address or user ID
narrativeNoOptional description/narrative for the objective
permissionNoVisibility, comma-separated. Team objectives accept team/report/internal/any; personal objectives accept owner/manager. Defaults by type when omitted (team → "internal,team", individual → "owner").
start_dateYesStart date in YYYY-MM-DD format
key_resultsNoOptional list of key results, each with a name and optional start_value, target_value, and unit_type
target_dateYesTarget completion date in YYYY-MM-DD format
objective_typeNo"team" (default) or "individual"team

Output Schema

NameRequiredDescriptionDefault

No arguments

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed9 schema fields changedv0.12.0
    • removedInput schema / properties / goal_type
      Removed value: -{
      -  "default": "1",
      -  "description": "\"1\" for Team objective (default), \"2\" for Personal objective",
      -  "type": "string"
      -}
    • changedInput schema / properties / key_results / anyOf
      Previous value: -[
      -  {
      -    "items": {
      -      "additionalProperties": {
      -        "type": "string"
      -      },
      -      "type": "object"
      -    },
      -    "type": "array"
      -  },
      -  {
      -    "type": "null"
      -  }
      -]New value: +[
      +  {
      +    "items": {
      +      "additionalProperties": false,
      +      "description": "A key result to attach to a new objective.\n\nField names use OKR vocabulary; they are mapped to the WorkBoard API's\n``metric_*`` fields when the objective is created.",
      +      "properties": {
      +        "name": {
      +          "description": "Key result name",
      +          "maxLength": 255,
      +          "minLength": 1,
      +          "type": "string"
      +        },
      +        "start_value": {
      +          "anyOf": [
      +            {
      +              "maxLength": 20,
      +              "type": "string"
      +            },
      +            {
      +              "type": "null"
      +            }
      +          ],
      +          "default": null,
      +          "description": "Starting value (e.g. '0')"
      +        },
      +        "target_value": {
      +          "anyOf": [
      +            {
      +              "maxLength": 20,
      +              "type": "string"
      +            },
      +            {
      +              "type": "null"
      +            }
      +          ],
      +          "default": null,
      +          "description": "Target value (e.g. '100')"
      +        },
      +        "unit_type": {
      +          "anyOf": [
      +            {
      +              "maxLength": 255,
      +              "type": "string"
      +            },
      +            {
      +              "type": "null"
      +            }
      +          ],
      +          "default": null,
      +          "description": "Unit type (e.g. 'Number', 'Currency', 'Percent')"
      +        }
      +      },
      +      "required": [
      +        "name"
      +      ],
      +      "type": "object"
      +    },
      +    "type": "array"
      +  },
      +  {
      +    "type": "null"
      +  }
      +]
    • changedInput schema / properties / key_results / description
      Previous value: -"Optional list of key result dicts, each with keys like\n         \"metric_name\", \"metric_start\", \"metric_target\", \"metric_type\""New value: +"Optional list of key results, each with a name and optional\n         start_value, target_value, and unit_type"
    • addedInput schema / properties / objective_type
      Added value: +{
      +  "default": "team",
      +  "description": "\"team\" (default) or \"individual\"",
      +  "type": "string"
      +}
    • addedInput schema / properties / permission / anyOf
      Added value: +[
      +  {
      +    "type": "string"
      +  },
      +  {
      +    "type": "null"
      +  }
      +]
    • changedInput schema / properties / permission / default
      Previous value: -"internal,team"New value: +null
    • changedInput schema / properties / permission / description
      Previous value: -"Visibility setting (default \"internal,team\")"New value: +"Visibility, comma-separated. Team objectives accept\n        team/report/internal/any; personal objectives accept\n        owner/manager. Defaults by type when omitted (team →\n        \"internal,team\", individual → \"owner\")."
    • removedInput schema / properties / permission / type
      Removed value: -"string"
    • addedInput schema / properties / team
      Added value: +{
      +  "anyOf": [
      +    {
      +      "type": "string"
      +    },
      +    {
      +      "type": "null"
      +    }
      +  ],
      +  "default": null,
      +  "description": "Team ID (or name) — required for team objectives, ignored for individual"
      +}
  2. Addedv0.7.0

TDQS

A3.9/5.0
Behavior4/5

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

With no annotations, the description carries the whole burden and does so well: it discloses that objectives cannot be updated or deleted via API (mistakes persist until fixed in the UI), and corrects the auth assumption by stating an instant JWT token with isSuperUser:false can create objectives and check in key results. Weakness: the auth passage is framed as a correction of prior text rather than a clean statement, and nothing is said about failure modes or rate limits.

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

Conciseness3/5

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

The core purpose and team/key-result guidance is front-loaded and useful, but a substantial middle paragraph argues against a previously wrong description ('This used to say...That is wrong'), which is meta-commentary an agent must parse to extract the actual auth fact. Sentences earn partial credit but the framing is longer than needed.

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 9-parameter mutation tool with an output schema and full schema coverage, the description supplies the essential extras: irreversibility, auth eligibility, and team linkage. It omits any mention of permission/visibility defaults and error behavior, which 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.

Parameters4/5

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

Schema coverage is 100%, so baseline is 3, but the description adds meaning beyond the schema by stating that ``team`` is required for team objectives and ignored for individual ones, and by enumerating key-result sub-fields (name, start_value, target_value, unit_type) with example units. It says nothing about ``permission`` or ``objective_type`` defaults, which the schema covers but the prose does not reinforce.

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?

Opens with a specific verb+resource: "Create a new objective with optional key results," and immediately scopes it to Team or Individual objectives. The verb 'create' plus the objective resource makes it distinguishable from get/list/update siblings in the catalog, though it never names a sibling explicitly.

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?

Gives clear context: team objectives must pass ``team`` sourced from workboard_get_teams_tool, individual objectives ignore it, and key results are optional with targets. It also warns that no API update/delete exists, implying creation should be done carefully. It does not name explicit when-not alternatives beyond the team/individual split.

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