Skip to main content
Glama

Create count follow-up

create_count_follow_up

Create a recount of a count: a new count with new batches that expects the chosen lines to be counted again. Send line_ids to choose lines, or leave them out to use every line marked recount. Optional name (default " – recount"), assigned_to, due_at, and count_date. The same call with the same arguments returns the same follow-up instead of making another. Works on an applied count too. Returns the new count. 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>"
    },
    "name": "create_count_follow_up"
  }
}

Input Schema

NameRequiredDescriptionDefault
nameNo
due_atNo
count_idYes
line_idsNo
count_dateNo
assigned_toNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

A3.8/5.0
Behavior2/5

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

The description adds substantial context the annotations do not carry: the feature-gate prerequisite, the default name "<count name> – recount", applied-count support, and the return value. However, "The same call with the same arguments returns the same follow-up instead of making another" describes get-or-create dedup semantics, which conflicts with idempotentHint=false; that is a partial contradiction rather than a flat safety inversion, so it is penalized but not scored 1.

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?

Four sentences, front-loaded with the definition, then line selection, then the default/optional fields, then dedup behavior, return value, and prerequisite. No sentence is filler; each adds a fact an agent needs before invoking.

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 6-param mutation tool with no output schema, this covers what is created, what is returned ("Returns the new count"), the feature gate, and the applied-count edge case. The remaining gaps are the undocumented formats/semantics for count_id, due_at, and count_date, and the misleading idempotency statement, which keep it from a 5.

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 0%, so the description carries the full burden. It delivers the two highest-value semantics — line_ids selects lines and its omission means all recount-marked lines, plus the default for name — but count_id (the only required param), assigned_to, due_at, and count_date are only named, with no format or meaning given (the date pattern lives only in 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?

States a specific verb and resource ("Create a recount of a count") and then defines the concept operationally — a new count with new batches expecting the chosen lines to be counted again. That definition distinguishes it from create_count/apply_count without needing to open another schema.

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?

Gives explicit selection guidance for the key decision: "Send line_ids to choose lines, or leave them out to use every line marked recount," plus the precondition "Requires the stock plan feature" and the edge case "Works on an applied count too." It never names a sibling alternative (e.g. create_count) for the case where a fresh count rather than a recount is wanted, so it stops short of a 5.

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