Skip to main content
Glama

log_review

Record how well you recalled a problem, schedule its next FSRS revision, and journal mistakes to track recurring errors.

Instructions

Record how well the user recalled a problem, schedule the next revision with FSRS, and journal any mistakes made on the way.

    rating: again (could not solve it), hard (solved with real difficulty), good
    (solved after some thought) or easy (solved at once).

    The problem's title, link and tags are read from the platform itself. Give each
    mistake a short kind, reusing an existing one from mistake_kinds when it fits, and
    a note on what went wrong in the user's own words.

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": {
      "platform": "<platform>",
      "problem_id": "<problem_id>",
      "rating": "<rating>"
    },
    "name": "log_review"
  }
}

Input Schema

NameRequiredDescriptionDefault
ratingYes
mistakesNo
platformYes
problem_idYes

Output Schema

NameRequiredDescriptionDefault
dueYes
urlYes
titleYes
reviewsNo
platformYes
stabilityNo
difficultyNo
problem_idYes
retrievabilityNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed16 schema fields changedv0.2.0
    • addedInput schema / $defs / ReviewRating
      Added value: +{
      +  "enum": [
      +    "again",
      +    "hard",
      +    "good",
      +    "easy"
      +  ],
      +  "title": "ReviewRating",
      +  "type": "string"
      +}
    • removedInput schema / properties / quality
      Removed value: -{
      -  "maximum": 5,
      -  "minimum": 0,
      -  "title": "Quality",
      -  "type": "integer"
      -}
    • addedInput schema / properties / rating
      Added value: +{
      +  "$ref": "#/$defs/ReviewRating"
      +}
    • removedInput schema / properties / tags
      Removed value: -{
      -  "anyOf": [
      -    {
      -      "items": {
      -        "minLength": 1,
      -        "type": "string"
      -      },
      -      "type": "array"
      -    },
      -    {
      -      "type": "null"
      -    }
      -  ],
      -  "default": null,
      -  "title": "Tags"
      -}
    • removedInput schema / properties / title
      Removed value: -{
      -  "minLength": 1,
      -  "title": "Title",
      -  "type": "string"
      -}
    • removedInput schema / properties / url
      Removed value: -{
      -  "format": "uri",
      -  "minLength": 1,
      -  "title": "Url",
      -  "type": "string"
      -}
    • changedInput schema / required
      Previous value: -[
      -  "platform",
      -  "problem_id",
      -  "title",
      -  "url",
      -  "quality"
      -]New value: +[
      +  "platform",
      +  "problem_id",
      +  "rating"
      +]
    • addedOutput schema / properties / difficulty
      Added value: +{
      +  "anyOf": [
      +    {
      +      "type": "number"
      +    },
      +    {
      +      "type": "null"
      +    }
      +  ],
      +  "default": null,
      +  "title": "Difficulty"
      +}
    • changedOutput schema / properties / due / format
      Previous value: -"date"New value: +"date-time"
    • removedOutput schema / properties / ease
      Removed value: -{
      -  "title": "Ease",
      -  "type": "number"
      -}
    • removedOutput schema / properties / interval_days
      Removed value: -{
      -  "title": "Interval Days",
      -  "type": "integer"
      -}
    • removedOutput schema / properties / repetitions
      Removed value: -{
      -  "title": "Repetitions",
      -  "type": "integer"
      -}
    • addedOutput schema / properties / retrievability
      Added value: +{
      +  "anyOf": [
      +    {
      +      "type": "number"
      +    },
      +    {
      +      "type": "null"
      +    }
      +  ],
      +  "default": null,
      +  "title": "Retrievability"
      +}
    • addedOutput schema / properties / reviews
      Added value: +{
      +  "default": 0,
      +  "title": "Reviews",
      +  "type": "integer"
      +}
    • addedOutput schema / properties / stability
      Added value: +{
      +  "anyOf": [
      +    {
      +      "type": "number"
      +    },
      +    {
      +      "type": "null"
      +    }
      +  ],
      +  "default": null,
      +  "title": "Stability"
      +}
    • changedOutput schema / required
      Previous value: -[
      -  "platform",
      -  "problem_id",
      -  "title",
      -  "url",
      -  "ease",
      -  "interval_days",
      -  "repetitions",
      -  "due"
      -]New value: +[
      +  "platform",
      +  "problem_id",
      +  "title",
      +  "url",
      +  "due"
      +]
  2. First observedv0.1.0

TDQS

A3.8/5.0
Behavior4/5

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

Annotations already declare readOnlyHint=false and idempotentHint=false, and the description adds real substance beyond that: it discloses that the call reschedules the next revision with FSRS and writes a mistake journal, and that title/link/tags are pulled from the platform rather than supplied. The notable gap is that with idempotentHint=false it never says what happens on a repeated log for the same problem — duplicate review entry or overwrite.

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?

The action summary is front-loaded in the first sentence, followed by the rating enumeration and mistake guidance — a logical order with no filler. The rating parentheticals are slightly dense inline but each one earns its place by disambiguating adjacent enum values.

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 an output schema present, return values need no explanation, and the description covers the write side-effects and the tricky parameters. It stops short of stating the precondition that the problem must already exist on the platform and how to resolve the platform identifier, which for a 3-required-param write tool is the remaining gap.

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 carry the load, and it does for the two non-obvious parameters: 'rating' gets a full enum explanation with recall-quality semantics, and 'mistakes' gets structure guidance (short kind, reuse from mistake_kinds, note in the user's own words). It only weakly explains 'platform' (no reference to list_platforms) and 'problem_id' format, so a small gap remains.

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 states three concrete actions with specific resources: recording recall quality, scheduling the next revision via FSRS, and journaling mistakes. An agent knows exactly what the call accomplishes, though it never explicitly distinguishes this from the sibling 'record_problem' (which presumably creates a problem entry) or 'progress', leaving boundary inference to the agent.

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?

Usage guidance is strong for the rating parameter — 'again (could not solve it), hard..., good..., easy...' gives clear conditions for each choice. It also directs the agent to reuse kinds from the 'mistake_kinds' sibling. However, there is no guidance on when to call this tool versus 'record_problem' or 'revisions_due', and no prerequisites (e.g., the problem must already exist on the platform) are stated.

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