Skip to main content
Glama

anti_pattern

Record mistakes and the correct approach to avoid repeating them, and let pulse() surface open pitfalls per domain.

Instructions

Record a mistake/temptation to avoid repeating, and the correct approach.

Stored as type='anti_pattern'; open ones for a domain are surfaced by pulse(). also cross-lists it into further domain paths, review_after dates when to recheck it and source_ref says what it came from -- see note().

ONE pitfall per memory: a second temptation from the same session is its own anti_pattern(), connected with link_memories(). See note() on what a body holds and when it is two memories.

title: one line naming what this memory is about, in the words someone would look for it by. It is what a list shows instead of the opening of the body, and it outweighs every other field in search, so a title that repeats the type ("note about the parser") names nothing. At most 120 characters, and a name that needs more than that is summarizing the body instead of naming it.

tags carries the synonyms the body never uses: retrieval is BM25 over content and tags, so a memory with none is reachable only by quoting itself. See note() for what belongs there.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
alsoNo
tagsNo
titleYes
domainNo
insteadYes
patternYes
sessionNo
why_wrongYes
source_refNo
review_afterNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed6 schema fields changedv0.1.1
    • addedInput schema / properties / also
      Added value: +{
      +  "default": "",
      +  "title": "Also",
      +  "type": "string"
      +}
    • addedInput schema / properties / review_after
      Added value: +{
      +  "default": "",
      +  "title": "Review After",
      +  "type": "string"
      +}
    • addedInput schema / properties / source_ref
      Added value: +{
      +  "default": "",
      +  "title": "Source Ref",
      +  "type": "string"
      +}
    • addedInput schema / properties / tags
      Added value: +{
      +  "default": "",
      +  "title": "Tags",
      +  "type": "string"
      +}
    • addedInput schema / properties / title
      Added value: +{
      +  "title": "Title",
      +  "type": "string"
      +}
    • changedInput schema / required
      Previous value: -[
      -  "pattern",
      -  "why_wrong",
      -  "instead"
      -]New value: +[
      +  "title",
      +  "pattern",
      +  "why_wrong",
      +  "instead"
      +]
  2. First observedv0.1.0

TDQS

A3.7/5.0
Behavior3/5

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

No annotations are provided, so the description carries full burden. It discloses key behavioral traits: storage type is 'anti_pattern', open ones surfaced by pulse(), cross-listing via 'also', review_after semantics, source_ref meaning, and the one-pitfall-per-memory rule. However, it doesn't describe permissions, mutation/reversibility, or return format for a creation tool with 10 params.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness3/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is fairly long and contains several paragraphs, but each has purpose. It front-loads the core purpose, then details parameters. However, some sentences are verbose and repetitively reference 'see note()' three times, and the structure mixes usage rules with parameter semantics without clear separation.

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?

Given 10 parameters with 0% schema coverage, no annotations, and no output schema, the description does a good job covering the creation semantics, critical constraints (one pitfall per memory), retrieval behavior, and most parameter meanings. It still leaves some parameters (pattern, why_wrong, instead, domain, session) unexplained, which for a 10-param tool leaves notable gaps.

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 0%, so the description must compensate. It does add meaning for multiple params: clarifies 'title' semantics (one line, max 120 chars, outweighs others in search), 'also' cross-lists into further domains, 'review_after' dates rechecking, 'source_ref' says origin, 'tags' carries synonyms for BM25 retrieval. However, it doesn't explain 'pattern', 'why_wrong', 'instead', 'domain', or 'session' directly, and 0% schema coverage means some gaps remain.

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 clearly states a specific verb+resource: recording a mistake/temptation to avoid repeating, plus the correct approach. It also names the storage type ('anti_pattern') and the surfacing mechanism via pulse(). It's not fully distinguished from note() and link_memories() which are referenced but not contrasted, so a 4 rather than 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 Guidelines4/5

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

It provides clear context: open ones are surfaced by pulse(), it explicitly says ONE pitfall per memory and that a second temptation should be its own anti_pattern() connected with link_memories(). It points to note() for related concepts but never explicitly states when to use this tool versus alternatives like note(). Solid but lacks explicit exclusions.

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