Skip to main content
Glama

set_play_record

Add or update a single Play Records entry for a game, including names, values, checkboxes, progress, table rows, text, and earned dates. Use row index or matching name to update existing records.

Instructions

Add or update one row in a Play Records category. action: add or update (update needs row_index, 1-based, or a matching name). keyValue: name + value. checkbox: name + unlocked=true/false (value=true also works). progress: name + progress_earned/progress_total (or value "3/10"), optional description. table: values as JSON array or "a | b | c". text: content (or value). earned_date YYYY-MM-DD where the category allows dates.

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": {
      "slug": "<slug>",
      "category": "<category>"
    },
    "name": "set_play_record"
  }
}

Input Schema

NameRequiredDescriptionDefault
nameNo
slugYes
valueNo
actionNoadd
valuesNo
contentNo
wait_msNo
categoryYes
unlockedNo
row_indexNo
descriptionNo
earned_dateNo
collection_idNo
progress_totalNo
progress_earnedNo

Output Schema

NameRequiredDescriptionDefault
resultYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed8 schema fields changedv2.1.0
    • addedInput schema / properties / content
      Added value: +{
      +  "default": "",
      +  "title": "Content",
      +  "type": "string"
      +}
    • addedInput schema / properties / description
      Added value: +{
      +  "default": "",
      +  "title": "Description",
      +  "type": "string"
      +}
    • addedInput schema / properties / earned_date
      Added value: +{
      +  "default": "",
      +  "title": "Earned Date",
      +  "type": "string"
      +}
    • addedInput schema / properties / progress_earned
      Added value: +{
      +  "default": "",
      +  "title": "Progress Earned",
      +  "type": "string"
      +}
    • addedInput schema / properties / progress_total
      Added value: +{
      +  "default": "",
      +  "title": "Progress Total",
      +  "type": "string"
      +}
    • addedInput schema / properties / unlocked
      Added value: +{
      +  "default": "",
      +  "title": "Unlocked",
      +  "type": "string"
      +}
    • addedInput schema / properties / values
      Added value: +{
      +  "default": "",
      +  "title": "Values",
      +  "type": "string"
      +}
    • changedInput schema / properties / wait_ms / default
      Previous value: -3000New value: +0
  2. First observedv1.0.1

TDQS

A3.5/5.0
Behavior3/5

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

With no annotations at all, the description carries the full disclosure burden and does partially meet it by explaining the add-vs-update distinction and the row-addressing rule. It omits important behavior: whether an update overwrites unspecified fields, what happens when the name matches multiple rows, whether errors are raised for unknown categories, and what wait_ms does. That is a meaningful gap for a mutation tool with zero annotation coverage.

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 purpose is front-loaded in the first clause, followed by a compact category-to-parameter mapping that is well organized by record type. The dense run-on punctuation ('action: add or update (update needs row_index, 1-based, or a matching name)') makes it harder to parse than a bulleted list would be, but nearly every word carries required information given 15 undocumented parameters.

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

Completeness3/5

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

An output schema exists, so return values need not be explained, and the description covers the bulk of the per-category parameter combinations. Against 15 parameters with 0% schema coverage and no annotations, the missing coverage of slug, category, collection_id, and wait_ms, plus absent error/upsert semantics, leaves the definition short of fully self-sufficient.

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 all parameter meaning, and it does a substantial job: it maps category-specific field combinations (name+value, name+unlocked, name+progress_earned/progress_total, values as JSON or pipe-delimited, content, earned_date format, row_index, description). It leaves slug, category, collection_id, and wait_ms unexplained, which prevents a 5 but the compensation is well above baseline.

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 first sentence gives a specific verb and resource: 'Add or update one row in a Play Records category,' which tells an agent exactly what is mutated and at what granularity (a single row). It does not explicitly contrast itself with the sibling set_play_record_category or remove_play_record, so sibling differentiation is left implicit, keeping it below 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 Guidelines3/5

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

The description gives real operational guidance for the action parameter, noting that update requires a 1-based row_index or a matching name, which is genuinely useful selection logic. However, it never says when to choose this tool over set_play_record_category, copy_play_records, or set_game_progress, so guidance is limited to intra-tool parameter choice rather than tool-level alternatives.

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