Skip to main content
Glama

lessons

Recall distilled decisions, mistakes with corrections, and how-tos learned before, ranked by relevance, importance, and recency with citations; filter by type or include retired entries.

Instructions

Recall distilled lessons — decisions, mistakes+corrections, how-tos learned before.

    Higher-signal than raw chat recall: ranked by relevance × importance × recency, each with
    citations. ``type`` filters ``decision`` | ``mistake`` | ``howto``. ``include_retired`` also
    returns deprecated/superseded lessons (hidden by default) with their ``deprecated_reason``
    and ``superseded_by`` breadcrumb — use it to check *why* something was retired.
    

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": {
      "text": "<text>"
    },
    "name": "lessons"
  }
}

Input Schema

NameRequiredDescriptionDefault
kNo
textYes
typeNo
include_retiredNo

Output Schema

NameRequiredDescriptionDefault
resultYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.0.0

TDQS

A4.1/5.0
Behavior4/5

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

With no annotations, the description carries the burden and does real work: it discloses the ranking formula (relevance × importance × recency), that results carry citations, and the non-obvious default that retired/superseded lessons are hidden unless opted in, plus the `deprecated_reason`/`superseded_by` fields returned. It doesn't state that the call is read-only in effect or describe result volume/pagination, but the output schema covers return shape.

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?

Front-loaded with the identity of the tool and the differentiator before the parameter notes; every sentence adds information. Minor redundancy in the double framing ("distilled" plus the raw-recall comparison) and heavy backtick formatting, but nothing wasted.

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 read-only retrieval tool with an output schema, the description covers purpose, ranking behavior, filtering, and the retired-lesson edge case. The only material gap is what `text` should contain and what `k` controls, which the agent needs in order to call it correctly.

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

Parameters3/5

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

Schema coverage is 0%, so the description must compensate. It does well on two of four params — `type` is given concrete enum values (decision | mistake | howto) that the schema lacks, and `include_retired` gets its default and the breadcrumb fields it unlocks. The required `text` query parameter and the `k` result-count (default 5) are left entirely unexplained.

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 verb+resource ("Recall distilled lessons") and immediately enumerates what a lesson is — decisions, mistakes+corrections, how-tos. It also positions itself against the `recall` sibling by claiming higher signal than raw chat recall, so an agent can pick between them without opening schemas.

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 a clear use context (distilled, ranked lessons rather than raw chat) and an explicit when-to-use for `include_retired`: "use it to check *why* something was retired." It stops short of stating when to prefer a different sibling (e.g. add_learning vs lessons), but the retrieval scenario is unambiguous.

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