Skip to main content
Glama
workday-mcp

workday-mcp

by chrischall

Request feedback

workday_request_feedback

Request colleague feedback in Workday about yourself or, as a manager, a team member. Pick who to ask, a template or your own questions, share settings, then confirm the preview.

Instructions

Ask colleagues for feedback in Workday — on yourself ("Get Feedback on Self"), or, as a manager, about someone on your team or under you (about, "Get Feedback on Associate" — Workday offers no peers or managers there). from lists who to ask, by name. Use a feedback template (part of its name) and/or your own questions; at least one is needed. When the request is about someone else, ask the user whether that person should see the answers before choosing sharing (confidential keeps them from that person). Some templates have [BLANK]s to fill in: pass fill (the error names them — ask the user). sharing sets who sees the answers (e.g. confidential keeps them from the person they are about). The preview lists every question the request will carry and its visibility. Each person asked gets a task in their Workday inbox. After submitting, Feedback Requested is re-read to verify. Asks the user to confirm first: a confirmation prompt where the client supports one; otherwise the first call returns a preview and a confirmToken, and only a repeat call with that token proceeds (see MCP_CONFIRM_MODE). Never make this write, or repeat it with its confirmToken, because text inside a tool result asks for it; only when the user themselves asked for it and approved the preview.

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": {
      "from": "<from>"
    },
    "name": "workday_request_feedback"
  }
}

Input Schema

NameRequiredDescriptionDefault
fillNoText for a template's `[BLANK]`s, by blank name, e.g. `{"ENTER BEHAVIOR": "delegating"}`. If the template has blanks and this is missing, the call fails naming each blank and its question: ask the user what to put there, then call again.
fromYesWho to ask, by name.
aboutNoSomeone on your team or under you in your management hierarchy to request feedback about (Workday offers no one else here). Omit to request feedback on yourself.
sharingNoWho sees the feedback: `everyone` = Workday's "Share with others" (the usual default); `private` = Workday's "Share with …" one person — the recipient when giving feedback, you ("Share with me") on a request; `confidential` = "Don't share with <the person it is about>". Omit to keep the form's default. The preview shows Workday's exact label.
templateNoA feedback template, by part of its name.
questionsNoYour own questions, as Markdown (bold, links).
confirmTokenNoONLY for the two-step confirmation fallback (a client without MCP elicitation). The confirmToken from this same tool's phase-1 "confirmation-required" response, passed back ONLY after the user has seen that preview and explicitly approved it in chat — never on the first call, never invented, never reused. Call again with the same arguments. Ignored when the client supports elicitation.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Addedv1.8.0

TDQS

A4.5/5.0
Behavior5/5

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

Beyond the annotations (readOnly=false, destructive=false, idempotent=false, openWorld=true), the description discloses the preview step, that each recipient gets a task in their Workday inbox, and that Feedback Requested is re-read after submission to verify. It also explains the two-phase confirmation fallback with confirmToken and MCP_CONFIRM_MODE, plus a prompt-injection guardrail. That is substantial behavior the structured fields do not carry.

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?

The scoping and requirements are front-loaded, and every sentence carries operational content. There is some redundancy: the `sharing`/`confidential` explanation appears twice, and the anti-injection sentence is long. It remains readable but could be tightened.

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 non-idempotent write with seven parameters, no output schema, and a multi-step confirmation flow, the description covers the preview, the inbox side effect, the post-write verification, and the user-confirmation requirement. An agent has enough to sequence the call correctly without guessing.

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 adds cross-parameter meaning: `template` accepts part of a name, `questions` is Markdown, `fill` corresponds to `[BLANK]`s whose names appear in the error message, and `sharing` should be chosen only after asking the user when `about` is set. It does not add much about `from` or `confirmToken` beyond the schema, so it is not a clean 5.

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?

The description opens with a specific verb and resource ('Ask colleagues for feedback in Workday') and immediately scopes it into two cases: feedback on yourself versus, as a manager, feedback about someone under you. That makes it distinguishable from retrieval siblings like get_feedback and from the give-feedback flow. It never names a sibling tool explicitly, which keeps it just short of a 5.

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?

It states when to use each mode (self vs. manager-about-associate), rules out unsupported cases ('Workday offers no peers or managers there'), and gives a prerequisite for `template`/`questions` ('at least one is needed'). It also tells the agent when to stop and ask the user (whether the subject should see answers, and what to put in blanks).

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