Skip to main content
Glama

Remember what they read, watched or played

remember
Destructive

Save something the person just told you about their own reading, watching, listening or playing, in one call: "just finished Severance, loved it", "started Dune", "gave up on that podcast", "rewatched Heat last night", "want to read Piranesi". Finds the title in their library (exact title, or item_id) or adds it, then sets what happened, the date and the rating. Use it for the person's own activity, not for titles you are only discussing or recommending. Afterwards tell them in a few words what you saved.

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": {
      "media_type": "<media_type>",
      "happened": "<happened>"
    },
    "name": "remember"
  }
}

Input Schema

NameRequiredDescriptionDefault
dateNoWhen it happened: YYYY-MM-DD, or YYYY-MM or YYYY when that is all they said. Work it out from what they said ("last night" is yesterday). Left out, a finish is dated today; for one long ago ("back in college"), give the year.
noteNoFor again: a short note about this time, in their words
yearNoRelease year, when known; tells a remake from the original
titleNoThe title as they said it (exact title preferred)
ratingNoOnly when they gave one or said something that clearly maps to stars ("loved it" is not a number: ask, or leave it out)
creatorNoAuthor/artist/director/creator, when known; helps find the right one
item_idNoLibrary item id (UUID), when you already have it. Title is then ignored.
happenedYesfinished (read/watched/played it), started (in the middle of it), want (wants to get to it), gave_up (stopped partway), again (another read/watch/listen of something they had finished before)
media_typeYesType of media. Use anime (not show) for Japanese animation.
external_idNoExternal id from lookup_item, for an exact match when adding

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • changedInput schema / properties / media_type / enum
      Previous value: -[
      -  "book",
      -  "movie",
      -  "album",
      -  "show",
      -  "anime",
      -  "podcast",
      -  "game",
      -  "manga",
      -  "comic"
      -]New value: +[
      +  "book",
      +  "movie",
      +  "album",
      +  "show",
      +  "anime",
      +  "podcast",
      +  "game",
      +  "manga",
      +  "comic",
      +  "boardgame"
      +]
  2. Changed1 schema field changed
    • changedInput schema / properties / media_type / enum
      Previous value: -[
      -  "book",
      -  "movie",
      -  "album",
      -  "show",
      -  "anime",
      -  "podcast",
      -  "game",
      -  "manga"
      -]New value: +[
      +  "book",
      +  "movie",
      +  "album",
      +  "show",
      +  "anime",
      +  "podcast",
      +  "game",
      +  "manga",
      +  "comic"
      +]
  3. Changed1 schema field changed
    • changedInput schema / properties / date / description
      Previous value: -"When it happened: YYYY-MM-DD, or YYYY-MM or YYYY when that is all they said. Work it out from what they said (\"last night\" is yesterday). Omit if unknown."New value: +"When it happened: YYYY-MM-DD, or YYYY-MM or YYYY when that is all they said. Work it out from what they said (\"last night\" is yesterday). Left out, a finish is dated today; for one long ago (\"back in college\"), give the year."
  4. Changed2 schema fields changed
    • changedInput schema / properties / rating / minimum
      Previous value: -0.5New value: +0.05
    • removedInput schema / properties / rating / multipleOf
      Removed value: -0.5
  5. Added

TDQS

A4.2/5.0
Behavior4/5

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

Beyond the annotations, the description explains the workflow: find the title in the library or add it, then set what happened, the date, and the rating. This adds useful mutation context, including that the tool may create a library item. It does not explicitly warn about overwriting existing status or rating or about duplicate matching, which are relevant given destructiveHint=true and idempotentHint=false.

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?

The description is front-loaded with the core action, then gives examples, the key usage exclusion, and a post-action instruction. The examples are compact and functional, and there is no obvious filler or repetition.

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 10-parameter mutation tool with no output schema and a destructive annotation, the description covers purpose, workflow, usage boundaries, and what to tell the user afterward. It leaves some operational ambiguity around duplicate matching and overwriting existing data, but the schema and annotations cover much of the remaining burden.

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 description coverage is 100%, so the schema already carries detailed meaning for parameters such as date, rating, happened, and media_type. The description repeats a few parameter ideas—exact title, item_id, date, rating—and its natural-language examples help map user phrasing to happened values, but it adds little semantic detail beyond the schema.

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 states a specific verb and resource: saving a person's own reading, watching, listening, or playing activity in one call. It supplies concrete examples such as finishing Severance or starting Dune, which make the scope immediately clear. It also distinguishes this from merely discussing or recommending titles.

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 gives clear use context for the person's own activity and an explicit exclusion for titles only being discussed or recommended. It does not name a specific alternative sibling tool, so the routing guidance is strong but not a full when-to-use-vs-alternative statement.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources