Skip to main content
Glama
Sign In
DeskCalc Verify

DeskCalc Verify

Official
by DeskCalc
OverviewSchemaSourceRelated ServersDiscussionsAdmin
JavaScript
Local

Save the audit record (PDF)

save_audit_record

Saves a confirmed verification as a PDF audit record for working papers, including document details, calculations, corrections, and cent-exact checks, then returns the local file path.

Instructions

Save a confirmed verification as a PDF audit record for the working papers: document name, date and user, every line with its calculation, the user's corrections and the cent-exact document check. Saved locally in the DeskCalc Verify folder; returns the file path.

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": {
      "review_id": "<review_id>"
    },
    "name": "save_audit_record"
  }
}

Input Schema

NameRequiredDescriptionDefault
noteNoShort note for the record, e.g. the client or the purpose of the check.
sourceNoThe checked document, e.g. "Invoice RE-2026-0001.pdf".
languageNoOmit: the record is written in the language DeskCalc runs in. Set only if the user explicitly asks for another language.
review_idYesreview_id of a confirmed verification.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A4.1/5.0
Behavior4/5

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

Annotations already declare write, non-destructive, non-idempotent, closed-world behavior. The description adds real context beyond that: the file lands locally in the "DeskCalc Verify" folder and the call returns the file path. It stops short of disclosing what happens on a repeat save (overwrite vs. duplicate file) or how an unconfirmed review_id fails, which matters given 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.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

A single front-loaded sentence with the deliverable first, followed by contents, storage location and return value. It is dense but every clause carries information; the mid-sentence content list is the only stretch that could be trimmed.

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?

No output schema exists, yet the description explicitly states the return value (file path) and the on-disk location, which is exactly what an agent needs. For a non-idempotent write tool, the remaining gap is failure and overwrite behavior rather than tool purpose.

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 per-parameter meaning is already carried by the schema, including the enum guidance on language. The description's content list (document name, date, user, lines, corrections, cent-exact check) describes what ends up in the PDF rather than adding meaning to specific parameters, so the baseline of 3 applies.

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?

"Save a confirmed verification as a PDF audit record" gives an explicit verb (save) and artifact (PDF audit record), then enumerates the record's contents. This is the only write/export tool among the siblings (verify_numbers, get_verification, compare_verifications, deskcalc_status), so an agent can route here unambiguously.

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?

The phrase "a confirmed verification" establishes the key prerequisite and implicitly steers the agent away from unverified reviews. It also frames the purpose ("for the working papers"), but never names an alternative action or states when not to save, so there is no explicit exclusion.

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

Deploy Server

Other Tools