Lovie Company Formation

Generate Cap Table Docs

cap_table_generate_cap_table_docs

Generates the SAFE agreement PDF for every SAFE holding of the given stakeholders (all of them when none are given). It runs synchronously: when it returns, queued_count agreements have rendered and are ready to prepare for signature, and failed_count agreements could not be rendered and are left FAILED. Whenever failed_count is above zero, tell the user those SAFEs were not generated rather than saying the documents are on their way. To retry, call this again with stakeholder_ids set to the previous response's failed_stakeholder_ids. Every call creates a new agreement for each SAFE holding of each stakeholder it is given, so repeating the original request duplicates SAFEs that already rendered, and an investor with several SAFE holdings has all of them rendered again, not only the one that failed.

Input Schema

TableJSON Schema

Name	Required	Description	Default
`companyId`	Yes	UUID value wrapper.
`stakeholderIds`	No

Output Schema

TableJSON Schema

Name	Required	Description	Default
`failedCount`	No
`queuedCount`	No
`failedStakeholderIds`	No

Schema Changelog

Changes observed during successful MCP inspections.

Changed2 schema fields changedSep 28, 2026

addedOutput schema / properties / failedCount
```
Added value: +{
+  "type": "integer"
+}
```

addedOutput schema / properties / failedStakeholderIds

Added value: +{
+  "items": {
+    "description": "UUID value wrapper.",
+    "properties": {
+      "value": {
+        "format": "uuid",
+        "type": "string"
+      }
+    },
+    "type": "object"
+  },
+  "type": "array"
+}

First observedAug 11, 2026

TDQS

A4.3/5.0

Behavior5/5

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

Goes well beyond the thin annotations (openWorldHint=false, destructiveHint=false) by disclosing synchronous execution, what queued_count and failed_count mean, how FAILED holdings should be reported to the user, and the critical idempotency caveat that re-running duplicates already-rendered SAFEs for every holding, not just the failed one.

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?

Front-loads what it generates and its synchronous nature, then the failure-handling and duplication rules. Dense but each sentence carries a distinct operational rule; the final duplication sentence is long though justified by the risk it prevents.

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?

Output schema already documents return fields, so the description needn't restate them, and it instead supplies the decision-relevant context (sync timing, failure reporting, retry path, duplication risk). Complete enough for an agent to call and interpret results correctly.

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?

With 50% schema coverage, the description compensates by defining the semantics of stakeholder_ids (all stakeholders when omitted, retry via failed_stakeholder_ids) and implying companyId scoping. The nested UUID wrapper structure is left to the schema, which is acceptable boilerplate.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb (generates), resource (SAFE agreement PDF), and scope (every SAFE holding of the given stakeholders, all of them when none are given). It is clearly distinct from the summary-PDF and single-agreement siblings in effect, but it never names them, so the differentiation is inferential rather than explicit.

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 clear operating context: call with no stakeholder_ids to cover everyone, and re-call with failed_stakeholder_ids to retry. It does not explicitly say when to prefer the sibling generate_cap_table_agreement_pdf or download_cap_table_safes, so the routing guidance is incomplete for a crowded cap-table namespace.

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

All Lovie Company Formation tools Inspect

Try in Browser

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.