Skip to main content
Glama
fitz2882

learned-experience

by fitz2882
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Hybrid

Record an experience

record

Save problem-solving outcomes to a shared experience base; automatically merge duplicates and link alternative fixes to prevent repeating past mistakes.

Instructions

Store what happened after solving (or failing to solve) a non-trivial problem. Duplicates are merged automatically: the response says whether the record was created, merged into an existing one, or linked to one with a different fix. Keep it terse and never include secrets.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
fixNoWhat finally worked, concrete enough to repeat. Omit if unresolved.
kindNo'episode' (default) or 'rule' for a generalisation of several episodes
avoidNoWhat did not work or made things worse
claimsNo
sourceNoProvenance: which agent/model is recording
contextNoTags: language, framework, tool, OS, domain. e.g. ['node','postgres','macos']
outcomeYes
problemYesOne-line statement of the problem, as generic as is accurate
signalsNoExact error messages, failing commands, or symptoms. These form the deterministic fingerprint.
attemptsNoOrdered attempts and whether each worked
root_causeNoWhy it happened, if known
observationsNo
applicabilityNo
preconditionsNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed4 schema fields changedv0.4.0
    • addedInput schema / properties / applicability
      Added value: +{
+  "additionalProperties": false,
+  "properties": {
+    "platform": {
+      "maxLength": 80,
+      "type": "string"
+    },
+    "product": {
+      "maxLength": 80,
+      "type": "string"
+    },
+    "project": {
+      "maxLength": 160,
+      "type": "string"
+    },
+    "version": {
+      "maxLength": 80,
+      "type": "string"
+    }
+  },
+  "type": "object"
+}
    • addedInput schema / properties / claims
      Added value: +{
+  "items": {
+    "properties": {
+      "key": {
+        "maxLength": 100,
+        "minLength": 1,
+        "type": "string"
+      },
+      "value": {
+        "maxLength": 200,
+        "minLength": 1,
+        "type": "string"
+      }
+    },
+    "required": [
+      "key",
+      "value"
+    ],
+    "type": "object"
+  },
+  "maxItems": 12,
+  "type": "array"
+}
    • addedInput schema / properties / observations
      Added value: +{
+  "items": {
+    "properties": {
+      "level": {
+        "enum": [
+          "reported",
+          "local-test",
+          "target-environment"
+        ],
+        "type": "string"
+      },
+      "observed_at": {
+        "format": "date-time",
+        "pattern": "^(?:(?:\\d\\d[2468][048]|\\d\\d[13579][26]|\\d\\d0[48]|[02468][048]00|[13579][26]00)-02-29|\\d{4}-(?:(?:0[13578]|1[02])-(?:0[1-9]|[12]\\d|3[01])|(?:0[469]|11)-(?:0[1-9]|[12]\\d|30)|(?:02)-(?:0[1-9]|1\\d|2[0-8])))T(?:(?:[01]\\d|2[0-3]):[0-5]\\d:[0-5]\\d(?:\\.\\d+)?(?:Z))$",
+        "type": "string"
+      },
+      "reference": {
+        "maxLength": 300,
+        "minLength": 3,
+        "type": "string"
+      },
+      "summary": {
+        "maxLength": 600,
+        "minLength": 3,
+        "type": "string"
+      }
+    },
+    "required": [
+      "summary",
+      "reference",
+      "observed_at",
+      "level"
+    ],
+    "type": "object"
+  },
+  "maxItems": 30,
+  "type": "array"
+}
    • addedInput schema / properties / preconditions
      Added value: +{
+  "items": {
+    "maxLength": 200,
+    "minLength": 1,
+    "type": "string"
+  },
+  "maxItems": 8,
+  "type": "array"
+}
  2. First observedv0.1.0

TDQS

A3.7/5.0
Behavior4/5

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

Annotations are all false and provide no safety or mutation context, so the description carries the burden. It explicitly discloses duplicate handling ('Duplicates are merged automatically'), response semantics (created/merged/linked), and a content constraint (no secrets), which goes beyond schema and annotations. It does not cover failure modes, but the key behavioral traits are well disclosed.

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?

Three sentences with no wasted words: the core action, duplicate behavior, and constraints are front-loaded. Every sentence earns its place, and the structure is easy for an agent to parse quickly.

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

Completeness2/5

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

For a 14-parameter write tool with no output schema and no meaningful annotations, the description is too thin. It covers the general trigger and duplicate behavior but does not orient the agent around required fields, nested-object structure, or how record differs from siblings like consolidate and amend. The response sentence helps partially, but it does not fully compensate for the missing output schema and large parameter surface.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters2/5

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

Schema description coverage is only 64%, and the description names no parameters, fields, or formats. Terms like 'what happened' only vaguely imply problem, outcome, fix, or attempts. It adds essentially no meaning beyond the schema's own property descriptions and does not compensate for the uncovered parameters.

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?

The description opens with 'Store what happened after solving (or failing to solve) a non-trivial problem', giving a specific write action and resource. It clearly separates this write operation from sibling read/delete tools like inspect, recall, forget, and dismiss. The purpose is unmistakable even though it does not name 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 Guidelines3/5

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

It states the trigger context: after solving or failing a non-trivial problem, and adds constraints like 'Keep it terse and never include secrets'. However, it never says when NOT to use record or which sibling to prefer, such as consolidate for merging, amend for editing, or recall/inspect for retrieval. With 13 siblings, that routing gap is significant.

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

Deploy Server

Other Tools