Completes Workday sign-in or account-creation dialogs at a job URL and fills supported signup forms using saved local profile credentials.
Handle an open Workday Sign In or Create Account dialog at the exact job URL, or fill a supported signup form. Credentials come from the local profile.
| Name | Required | Description | Default |
|---|---|---|---|
| site | Yes |
| Name | Required | Description | Default |
|---|---|---|---|
| state | Yes | ||
| sms_filled | No | ||
| signup_policy | No |
Changes observed during successful MCP inspections.
v0.1.0Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare destructiveHint=false and idempotentHint=false, and the description usefully adds that credentials are pulled from the local profile, so no credential parameters are needed. It does not disclose what happens on submission, whether an account is actually created on the external site, or how failures/unknown forms are reported – relevant for an action that registers accounts.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Two tight sentences with no filler, and the operative condition (open dialog at the exact job URL) is stated first. Minor ambiguity comes from the 'or' between the two modes rather than wasted wording.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
The output schema covers return values, but for a tool that drives registration/sign-in the description omits what 'Handle' entails (fill vs submit), which signup forms are 'supported', and what the caller should do on failure. Combined with an undocumented 'site' parameter, an agent cannot reliably invoke this without trial and error.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The single required parameter 'site' has 0% schema description coverage, and the description never explains what its value should be (a full job URL? a hostname? 'workday'?). The phrase 'at the exact job URL' is at best an indirect hint that the parameter is URL-shaped, which is not enough to compensate for the schema gap.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description names a concrete target (an open Workday Sign In or Create Account dialog at the exact job URL) plus a second mode (fill a supported signup form), so an agent can tell this is a browser-driving registration/login tool rather than a read-only receipt tool like its siblings. The verb 'Handle' is the weak point – it never says whether the tool fills fields, submits, or only detects the dialog.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
Usage is implied by state: call it when a Sign In/Create Account dialog is already open at the exact job URL. There are no explicit exclusions, no mention of the sibling tools (inspect_application_challenge, get_ashby_receipt, watch_ashby_receipt), and 'supported signup form' is never defined, leaving the agent to guess which sites qualify.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.