Skip to main content
Glama

muninn_table_records_import

Destructive

Import MANY records into one table in a single call. dryRun is TRUE BY DEFAULT - the first call validates and reports what would be written, and nothing is saved until you call again with dryRun:false. Validates the whole batch before writing anything and returns every error at once with its record index, so a bad cell costs one round trip, not one per record. Nothing is coerced: a checkbox field wants true/false, not the string TRUE. Pass upsertKey (field keys forming a natural key) with onConflict:update to make re-running the same import idempotent instead of duplicating everything. Writes are BUDGETED per call - the response carries remaining and nextIndex, and you re-send the tail from there. If the table is published with muninn_table_publish, committed records also appear on its public feed.

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": {
      "tableSlug": "<tableSlug>",
      "records": "<records>"
    },
    "name": "muninn_table_records_import"
  }
}

Input Schema

NameRequiredDescriptionDefault
tagsNoTags merged into every record's own tags.
dryRunNoTRUE BY DEFAULT. Validate and report without writing. Pass false to commit.
projectNoProject slug applied to every record that does not set its own.
recordsYesThe records to import, in order. Their INDEX in this array is what error messages and the per-record result refer to.
maxWritesNoHow many records to commit in THIS call. Defaults to 6, which keeps one call within the server's per-call limit. Call again to commit the rest.
tableSlugYesWhich table to import into. Must already be declared with muninn_table_define.
upsertKeyNoField keys forming a natural key, e.g. [source_file, worksheet]. Requires reading existing records, so it is refused on tables larger than 300 rows.
onConflictNoWhat to do when upsertKey matches an existing record. Only meaningful with upsertKey.error

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 flag this as a destructive, non-read-only write, and the description adds substantial context beyond them: dryRun defaulting to true, whole-batch validation with all errors returned at once by record index, no type coercion, budgeted writes with remaining/nextIndex, and the 300-row limit on upsertKey. The one wrinkle is idempotentHint:false versus the described opt-in idempotency, but the description scopes that strictly to upsertKey + onConflict:update rather than contradicting the annotation, so it is a nuance rather than a conflict.

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?

Front-loads the highest-risk fact (dryRun defaults to true and nothing is saved) before any secondary detail. Each sentence carries a distinct operational fact - validation behavior, type strictness, idempotency, budgeting, publication side effect - with no filler.

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?

For an 8-parameter mutation tool with no output schema, the description covers everything an agent must know to call it correctly: the validate-then-commit loop, partial-progress handling via nextIndex, error reporting shape, and the upsert size limit. Nothing essential about invoking it safely is missing.

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?

Schema coverage is 100%, so the baseline is 3; the description goes further by explaining the interplay between upsertKey and onConflict (only meaningful together) and by framing maxWrites as a per-call budget whose remainder is continued via nextIndex. It does not restate tableSlug or records semantics the schema already covers well.

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?

Opens with a specific verb, resource, and scope: 'Import MANY records into one table in a single call.' The emphasis on MANY and 'single call' implicitly separates it from the single-record sibling muninn_table_record_add, so an agent can pick between them without opening a 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 concrete procedural guidance: dryRun is true by default, so the first call validates and the second with dryRun:false commits; pass upsertKey with onConflict:update for idempotent re-runs; re-send the tail from nextIndex. It never explicitly names a sibling to use instead (e.g. muninn_table_record_add for one record), so routing guidance is strong but not fully comparative.

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