Skip to main content
Glama

Add count scans

add_count_scans

Add scans to a count. Use this to type in numbers a person read out. scans holds 1 to 500 entries of barcode and quantity (a whole number of 1 or more). Each entry is saved as its own scan and added to what is already counted, so a repeated call counts twice. Send one idempotency_key per logical submission (8 to 128 characters) and reuse the same key when you retry that submission after a timeout or error: the retry then saves nothing twice. A new key means new scans. quantity is at most 100000 per scan. Optional list_id is a batch of this count. Without it the scans go to a batch named " – added by assistant", which is created in count mode on the count's sheet and folder and attached to the count when the count has no open batch of that name. The count needs a sheet. Returns batch_id, how many scans were saved, and any skipped. Run compare_count afterwards. An applied count is read-only. Requires the stock plan feature.

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": {
      "count_id": "<count_id>",
      "scans": "<scans>"
    },
    "name": "add_count_scans"
  }
}

Input Schema

NameRequiredDescriptionDefault
scansYes
list_idNo
count_idYes
idempotency_keyNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

A4.7/5.0
Behavior5/5

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

Beyond the annotations it discloses the critical accumulation semantics ('a repeated call counts twice') and then explains how the idempotency_key guards retries against double-saving — resolving the apparent tension with idempotentHint=false rather than contradicting it. It also documents the implicit side effect of creating a default batch ('<count name> – added by assistant'), the per-scan quantity ceiling, and the read-only state of applied counts.

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 definition is dense but front-loaded, leading with the action, then entry constraints, then idempotency, then the optional batch behavior, then return values. Every sentence carries operational information, though the middle section packs several distinct rules into a single long block, which slightly hurts scannability.

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

Completeness5/5

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

There is no output schema, and the description covers returns itself (batch_id, how many scans were saved, any skipped), along with limits, side effects, preconditions, and the recommended next call. For a write tool with four parameters this leaves nothing material an agent would need before invoking it.

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

Parameters5/5

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

Schema description coverage is 0%, yet the description compensates fully: scans is bounded to 1–500 entries of barcode plus whole-number quantity capped at 100000, idempotency_key is 8–128 characters with explicit reuse-on-retry semantics, and list_id is defined as a batch of this count with a spelled-out fallback when omitted. That is meaning well beyond the raw JSON types.

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 opens with a specific verb and resource ('Add scans to a count') and immediately clarifies the input mode ('type in numbers a person read out'), which separates it from barcode-matching or listing tools. An agent knows exactly what this writes and to what parent object.

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 when-to-use context (manual entry of read-out numbers), a required follow-up step ('Run compare_count afterwards'), and hard preconditions (count needs a sheet, applied counts are read-only, stock plan feature required). It does not explicitly name an alternative sibling for barcode-driven entry, so routing between scan-adding tools is left partly to inference.

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