Skip to main content
Glama

Record an order in Provkeep (Record plan)

record_order
Destructive

Sends one order to the signed-in Record account, where it is checked against its state and kept with the rule that applied that day, exactly as POST /v2/checks does (https://provkeep.com/developers). Returns what each source says for each line and never holds or refuses the order. Send codes only: the order's reference, the two letter patient_state, and each line's product, dosage form, route and lot number. Never send a patient's or prescriber's name, address, date of birth or contact details.

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": {
      "code": "<code>",
      "patient_state": "<patient_state>",
      "lines": "<lines>"
    },
    "name": "record_order"
  }
}

Input Schema

NameRequiredDescriptionDefault
codeYesYour order reference. Not a patient identifier.
linesYes
purposeNo
placed_atNoWhen the order was placed, as an ISO time.
consult_typeNo
patient_stateYesThe two letter state the order ships to.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A3.7/5.0
Behavior4/5

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

Beyond annotations, it discloses substantive behavior: the record is state-checked but never blocked, the response reports per-source results per line, and the request must be de-identified. These are non-obvious traits an agent could not infer from the schema. It does not address why destructiveHint=true or warn that idempotentHint=false means a retried call can create a duplicate record.

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?

Three sentences, front-loaded with what happens to the order, then return behavior, then the data-minimization constraint. Dense but every sentence carries information; the endpoint URL is justified by the "exactly as POST /v2/checks does" parity claim. The title's parenthetical duplicates the opening sentence slightly.

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?

For a destructive, non-idempotent write with no output schema, the description covers persistence, non-blocking behavior, and a partial return summary, which is most of the burden. The clear gap is operational safety: no statement about duplicate submissions/retries, whether a recorded order can be corrected or undone, or what the account/auth requirement actually entails beyond "signed-in."

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?

At 50% schema coverage the description must compensate, and it does: it names the required fields (reference, two-letter patient_state, and per-line product, dosage form, route, lot number), which the schema leaves undescribed. It adds the meaningful norm "Send codes only" plus a PHI exclusion list the schema lacks. Gaps remain—purpose, placed_at, consult_type, quantity, and line_id are never mentioned, and "product" maps to the schema's "peptide" without saying so.

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?

"Sends one order to the signed-in Record account" states a concrete verb and resource, and "checked against its state and kept with the rule that applied that day" makes clear this persists a record rather than merely validating it. It stops short of naming precheck_order as the non-persisting alternative, so the boundary with the closest sibling is only implied.

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 context is implied by "kept with the rule that applied that day" and "never holds or refuses the order," which signals this is a post-decision recording step rather than a gate. However, there is no explicit "use this instead of precheck_order when..." routing, and no stated prerequisite ordering (e.g., precheck first, then record).

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