Skip to main content
Glama
logisky

logisheets-mcp

by logisky
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Local

create_block

Create a structured table on a sheet with typed columns, unique row keys, and initial rows. Auto-creates the sheet if missing, enabling formula references via block names.

Instructions

Create a structured block (table) on a sheet. fields[0] is the row-key column — the value BLOCKREF matches on, so it has to be unique per record; it is ordinary data you can write. Block ref name (name) is used as the first arg to BLOCKREF/BLOCKREFS in formulas.

Field types supported:

  • 'string' / 'number' — plain text/numeric cells.

  • 'boolean' — cell stores 0/1 or TRUE/FALSE; UI renders ✅/❌ if host has the widget set.

  • 'enum' (+ enum_id) — cell stores variant id; UI renders dropdown if host has the widget set. Watson auto-injects a variant-whitelist validation formula on the field so out-of-set writes light up as warnings even without widget rendering. Requires a prior define_enum_set call with matching id.

Rules (value_formula / validation / editability) are set separately via set_field_rule — this call only declares structure + initial rows. Auto-creates the target sheet if missing.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
nameYesBlock ref name. Used as the first arg to BLOCKREF/BLOCKREFS in formulas. Must be unique within the workbook.
sheetYesTarget sheet name.
fieldsYesColumn definitions in order. fields[0] is the row-key column.
positionYesTop-left cell of the block (0-indexed).
descriptionNoWhat this table is for, in a sentence or two: what a row represents, what the fields mean where the names are not obvious, and anything a later reader must not do to it (e.g. a field the craft maintains). Saved with the block and returned by describe_block, so write it for whoever opens the file next rather than for this conversation.
initial_rowsNoOptional initial rows.
unique_togetherNoField groups whose values must not repeat in COMBINATION — a rule about the TABLE, not about one cell. `unique` on a field covers one column; this covers several together, which nothing else can say. Reach for it on a fact table: a repeated (region, quarter) is an error nowhere, it just makes every total over that table quietly count twice. Violations show up in inspect__list_violations like any other rule.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed4 schema fields changedv0.5.0
    • addedInput schema / properties / fields / items / properties / description
      Added value: +{
+  "description": "What this field means, in a sentence, where the name alone does not say it — the unit it is in (\"in units of 10k\"), the convention it follows, or something a later reader must not do to it. Saved on the schema and returned by describe_block, so write it for whoever opens the file next rather than for this conversation.",
+  "type": "string"
+}
    • addedInput schema / properties / fields / items / properties / required
      Added value: +{
+  "default": false,
+  "description": "Every record must carry a value here. Declared on the schema, so every host and every later reader sees it.",
+  "type": "boolean"
+}
    • addedInput schema / properties / fields / items / properties / unique
      Added value: +{
+  "default": false,
+  "description": "No two records may carry the same value here. Declared on the schema.",
+  "type": "boolean"
+}
    • addedInput schema / properties / unique_together
      Added value: +{
+  "description": "Field groups whose values must not repeat in COMBINATION — a rule about the TABLE, not about one cell. `unique` on a field covers one column; this covers several together, which nothing else can say. Reach for it on a fact table: a repeated (region, quarter) is an error nowhere, it just makes every total over that table quietly count twice. Violations show up in inspect__list_violations like any other rule.",
+  "items": {
+    "items": {
+      "type": "string"
+    },
+    "type": "array"
+  },
+  "type": "array"
+}
  2. Changed1 schema field changedv0.1.1
    • addedInput schema / properties / description
      Added value: +{
+  "description": "What this table is for, in a sentence or two: what a row represents, what the fields mean where the names are not obvious, and anything a later reader must not do to it (e.g. a field the craft maintains). Saved with the block and returned by describe_block, so write it for whoever opens the file next rather than for this conversation.",
+  "type": "string"
+}
  3. First observedv0.1.0

TDQS

A4.9/5.0
Behavior5/5

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

Goes far beyond the sparse annotations by disclosing non-obvious behavior: auto-creation of the target sheet, auto-injection of an enum validation formula, and inference rules for field_type when omitted. It also explains UI rendering differences and the prerequisite define_enum_set, giving the agent a realistic model of side effects.

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?

The description is long, but it is front-loaded with a one-sentence purpose and organized into field-type and rule sections that justify the length. A small duplication of the `name` argument's BLOCKREF role between schema and prose keeps it from being perfectly lean.

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 a tool with 7 parameters, nested field objects, and no output schema, the description covers the tricky decisions: type inference, unique constraints, initial-row formatting, and the separation of rules. An agent has enough information to construct a valid block, including edge cases like enum fields and date ISO strings.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters5/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Even with 100% schema description coverage, the prose adds meaningful semantics: row-key uniqueness of fields[0], enum_id's dependency on define_enum_set, unique_together's purpose via the (region, quarter) example, and the handling of ISO date strings in initial_rows. This materially helps an agent fill the parameters correctly.

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 concrete action — 'Create a structured block (table) on a sheet' — and immediately defines the block's key structural trait (fields[0] as the row-key column). It is clearly distinct from sibling tools like set_field_rule and add_block_rows because it says what this call does and does not do.

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?

Explicitly tells the agent that value_formula/validation/editability rules belong to set_field_rule, not this tool, and that this call only declares structure plus initial rows. This is a clear when/where-to-go-next instruction, and the auto-create-sheet caveat prevents a false prerequisite.

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