Skip to main content
Glama

Lovie Company Formation

Import Cap Table

cap_table_import_cap_table

ImportCapTable writes a whole cap table in one call and one transaction: every row lands or none does, a row naming an existing holder is added to them (and reported as reused), a round the file names is recorded as closed history, and the result is refused if it would break the cap table's rules or does not match the totals the founder confirmed. Use this for any import of more than one holding instead of a sequence of single writes.

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": {
      "companyId": "<companyId>"
    },
    "name": "cap_table_import_cap_table"
  }
}

Input Schema

NameRequiredDescriptionDefault
rowsNo
replaceNo
companyIdYesUUID value wrapper.
roundTermsNo
expectedTotalSharesNo
expectedTotalCapitalNo

Output Schema

NameRequiredDescriptionDefault
rowsNo
removedNo
recordedRoundsNo
unpricedRoundsNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • addedInput schema / properties / rows / items / properties / security / properties / vesting / properties / vestedAtIssuanceShares
      Added value: +{
      +  "maximum": 10000000000,
      +  "minimum": 0,
      +  "type": "integer"
      +}
  2. Changed2 schema fields changed
    • addedInput schema / properties / roundTerms
      Added value: +{
      +  "items": {
      +    "properties": {
      +      "postMoneyValuation": {
      +        "maxLength": 50,
      +        "pattern": "^([0-9]+(\\.[0-9]{1,6})?)?$",
      +        "type": "string"
      +      },
      +      "preMoneyValuation": {
      +        "maxLength": 50,
      +        "pattern": "^([0-9]+(\\.[0-9]{1,6})?)?$",
      +        "type": "string"
      +      },
      +      "pricePerShare": {
      +        "maxLength": 50,
      +        "pattern": "^([0-9]+(\\.[0-9]{1,6})?)?$",
      +        "type": "string"
      +      },
      +      "roundName": {
      +        "maxLength": 255,
      +        "minLength": 1,
      +        "type": "string"
      +      }
      +    },
      +    "type": "object"
      +  },
      +  "maxItems": 100,
      +  "type": "array"
      +}
    • addedOutput schema / properties / unpricedRounds
      Added value: +{
      +  "items": {
      +    "type": "string"
      +  },
      +  "type": "array"
      +}
  3. Added

TDQS

A4.2/5.0
Behavior4/5

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

Annotations only declare openWorldHint=false and destructiveHint=false, so the description must carry the behavioral burden, and it does: all-or-nothing atomicity, deduplication of existing holders reported as 'reused', rounds recorded as closed history, rule validation, and refusal on total mismatch. The notable gap is the `replace` flag — a potentially destructive overwrite mode that the description never mentions, which sits awkwardly next to destructiveHint=false.

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?

Two sentences, no filler, and the atomicity guarantee is front-loaded before the edge-case behaviors. Each clause carries distinct information (atomicity, dedupe, round history, rule validation, totals check) rather than restating the tool name.

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?

For a complex nested-schema import tool with an output schema (so return values need no explanation), the description covers the important semantics: transactionality, holder reuse, and the validation gate. It falls short only on the `replace` mode, which an agent could trigger without understanding its effect.

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 only 17% across 6 parameters, so the description should compensate more than it does. It implicitly explains rows (per-row reuse semantics), roundTerms (rounds named by the file), and expectedTotalShares/expectedTotalCapital (the confirmed totals that gate the write), but `replace` and the deep nested `security` object go entirely unexplained.

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?

The description opens with a specific verb and resource ('writes a whole cap table') and immediately pins the scope to a single call and single transaction. That atomic framing distinguishes it from the many single-entity tools in the sibling list (create_cap_table_stakeholder, delete_cap_table_security, etc.).

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 closing sentence gives an explicit usage rule: 'Use this for any import of more than one holding instead of a sequence of a sequence of single writes,' which both states when to use it and names the alternative approach. It stops short of naming specific sibling tools or stating when NOT to use it (e.g., single-holder corrections), so it falls just below the top band.

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.