Skip to main content
Glama

log_learning

Log new Workday Studio patterns, schema rules, errors, and workarounds to a generalized shared knowledge base so teammates avoid repeating the same debugging.

Instructions

CALL THIS AUTOMATICALLY whenever you discover a new Workday Studio pattern, schema rule, gotcha, or workaround during a build session — even if the user did not ask you to log it. This is how the team's shared knowledge base grows. Examples of when to call this: a build fails with an error not already in the step-type reference, Studio silently rejects an element, MVEL throws an unexpected exception, a diagram crashes on open, a workaround fixes something with no documented cause. Do NOT call it for things already documented in get_step_type_reference or docs/studio-integration-patterns.md.

PUBLIC-REPO RULE — GENERALIZE EVERY FIELD: learnings.md is published in a public repository used across clients. Never include client integration IDs (use INT999), project names, tenant or environment names (use ), custom field names, or run/log identifiers. Describe provenance generically ("verified in a live run", "observed in a production build") — the technical pattern is the value, not where it came from.

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": {
      "title": "<title>",
      "category": "<category>",
      "trigger": "<trigger>",
      "pattern": "<pattern>",
      "promote_to": "<promote_to>"
    },
    "name": "log_learning"
  }
}

Input Schema

NameRequiredDescriptionDefault
titleYesShort descriptive title, e.g. "cc:splitter cannot have routes-to attribute"
exampleNoMinimal XML/MVEL/XSLT snippet showing the correct or incorrect form
patternYesWhat we learned — specific and actionable, written for a teammate who will hit this next
triggerYesWhat caused the discovery — the exact error or unexpected behavior observed
categoryYesThe type of learning
promote_toYesWhich file(s) this should be promoted into during the next review

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv1.8.0

TDQS

A4.6/5.0
Behavior4/5

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

No annotations are supplied, so the description carries the full burden, and it does disclose the key behavioral trait: the write lands in learnings.md, which is published in a public repo shared across clients. It also constrains provenance phrasing ('verified in a live run'). It stops short of saying whether entries are appended, deduplicated, or confirmed back to the caller, and gives no failure mode.

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?

Front-loaded with the imperative 'CALL THIS AUTOMATICALLY', then triggers, then exclusions, then a clearly headed constraint block. The one soft sentence ('This is how the team's shared knowledge base grows') is short motivational framing that supports the auto-invoke instruction rather than 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?

With six parameters at full schema coverage and no output schema, the description needs to cover invocation policy and content constraints, which it does thoroughly. Minor gaps remain: whether duplicate learnings are rejected, and what the tool returns or where the file lives.

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 description coverage is 100%, so the baseline is 3, but the description adds real meaning beyond it: the PUBLIC-REPO rule applies a scrubbing requirement to every field, with concrete substitution examples (INT999, <TENANT>) and a required style for provenance. That is semantic guidance the schema does not express.

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 action (log a discovery) against a specific resource (the shared learnings knowledge base) and enumerates the qualifying content types: Studio patterns, schema rules, gotchas, workarounds. It distinguishes itself from siblings by naming get_step_type_reference and the docs file as things this tool is not for.

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?

Gives explicit when-to-call triggers (build fails with an undocumented error, Studio silently rejects an element, MVEL throws an unexpected exception, diagram crashes on open, undocumented workaround) and an explicit when-not-to-call rule pointing at get_step_type_reference and docs/studio-integration-patterns.md. It even resolves the 'user didn't ask' ambiguity by instructing automatic invocation.

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