Skip to main content
Glama

Update import mapping

update_import_mapping
Idempotent

Correct an import's column mapping without re-uploading: {source_column: vepathos_field}, or {field, unit, format} for a column in another unit (lb, in, l) or date/number format. When the user corrects a unit ('those were cm3'), fix it here, never by converting the rows yourself. Returns the updated summary.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
mappingYesSource column → vepathos field, null to ignore the column, or {field, unit, format} when its values are in another unit or format.
import_idYesThe import to correct, from import_deliveries.

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
errorNo
statusNo
plan_idNoThe plan this lives in, in the user's Vepathos account (list_plans).
summaryNo
progressNo
import_idNo
dataset_idNo
expires_atNoWhen dataset_id expires. The plan stays.
account_urlNoOpens the plan in the user's Vepathos account. Requires signing in; private to the account.
plan_replacedNoSet when the library was full: this plan was removed to make room. Tell the user its name.
plan_temporaryNoTrue when every library slot is kept or favorite: the plan lives outside the library and is deleted later. Tell the user.
charged_becauseNoWhy the next run is charged: no_billed_run, stops_changed (a stop was added or moved), allowance_used, window_closed or no_allowance.
poll_after_secondsNo
free_retries_allowedNoHow many other tries a charged run opens on this account plan (field name is historical; say 'other tries' / 'otros intentos', not that the run is free).
next_optimize_chargedNoTrue: the next run of this plan charges its stops to the monthly allowance. False: it is another try (same stops or fewer, within the 24 h window) — no stops charged. When speaking to the user: English 'another try', Spanish 'otro intento'; never call a run free.
free_retries_remainingNoOther tries left in the open 24 h window. 0 when no window is open. Tell the user the count and the deadline (free_retry_window_ends_at); do not call the run free.
free_retry_window_ends_atNoWhen the other-try window closes (UTC). Null when no window is open. Always mention this deadline when next_optimize_charged is false.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.5/5.0
Behavior4/5

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

Annotations already declare readOnlyHint=false, idempotentHint=true, and destructiveHint=false, so the safety profile is covered. The description adds that it returns an updated summary and emphasizes that rows are not converted, which is useful behavioral context beyond the annotations. No contradiction.

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?

Three sentences, all substantive, with the core purpose front-loaded and the critical unit-correction instruction near the end. No filler or redundant restatement of the title.

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?

With an output schema present, a fully documented input schema, and annotations covering idempotency and safety, the description supplies the missing behavioral context (no row conversion) and usage decision. Nothing an agent needs to call this correctly is missing.

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 the schema thoroughly documents the mapping object and its unit/format fields. The description adds the high-level mapping shapes and the 'never convert rows' nuance, but the schema already carries most semantic weight, so a baseline 3 is appropriate.

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 ('Correct'), a specific resource ('an import's column mapping'), and the key constraint 'without re-uploading', which distinguishes it from import_deliveries and get_import_result. The purpose is unambiguous and actionable.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

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

Gives explicit direction on when to use it ('When the user corrects a unit') and an explicit exclusion ('never by converting the rows yourself'). It also implies the alternative of re-uploading is not needed, which is clear guidance for agent selection.

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