Skip to main content
Glama

Lovie Company Formation

by co.lovie

Import RSA

cap_table_import_rsa
Destructive

Imports a signed Restricted Stock Purchase/Award Agreement (RSA) from an uploaded PDF and stores the document in S3. USE THIS (not ExtractRsaTermsOcr + CreateCapTableAgreement, and not RecordCapTableInvestment) whenever the user provides or uploads a signed RSA PDF. The grantee (founder/employee/advisor) MUST already exist as a cap-table stakeholder — this tool matches the document to an existing stakeholder by name and does NOT create one; if there is no match the import is rejected, so add the stakeholder first. Mandatory two-step human-in-the-loop flow: (1) call GetOcrUploadUrl with kind=RSA and mime_type=application/pdf, then upload the PDF bytes to the returned PUT URL; (2) call ImportRSA with preview=true and that source_s3_uri — this runs OCR and returns the extracted founder/company names and terms (shares, vesting, price_per_share, grant_date, 83b status, acceleration) plus the resolved grantee (matched_stakeholder_id, or would_create=true when no stakeholder matches) WITHOUT persisting anything; (3) PRESENT those terms to the user as a table, let them correct any value, and get explicit confirmation; (4) call ImportRSA again WITHOUT preview and the SAME source_s3_uri; pass rsa_terms_override with any user-corrected terms (omit it to accept the extracted terms as-is), and stakeholder_id to pin the matched grantee. This creates the common-stock holding with its vesting schedule (or updates the grantee's existing holding), records a signed RSA agreement, and links the PDF — atomically. Never skip the preview + confirmation step; never persist unreviewed OCR output. Empty string / 0 / false in the extracted terms means the value was not stated in the document — never fabricate.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
previewNo
companyIdYesUUID value wrapper.
sourceS3UriNo
stakeholderIdNoUUID value wrapper.
consentToAiReadNo
rsaTermsOverrideNo
newStakeholderNameNo

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
statusNo
createdNo
previewNo
securityIdNoUUID value wrapper.
agreementIdNoUUID value wrapper.
stakeholderIdNoUUID value wrapper.
consentVersionNo
consentBodyMarkdownNo

TDQS

A4.7/5.0
Behavior5/5

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

Annotations only indicate destructiveHint=true, but the description adds substantial behavioral context: it does not create a new stakeholder, rejects unmatched imports, requires preview and confirmation, treats empty/0/false as 'not stated', and details the atomic creation/update behavior. It also warns to never persist unreviewed OCR output. This goes well beyond the annotations and no contradiction exists.

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 front-loaded with a clear purpose statement and organized as a numbered step-by-step workflow. Every sentence adds valuable implementation guidance, such as the requirement to present terms to the user and get confirmation. It is at the upper bound of appropriate length but remains structured and easy to follow.

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?

Given the tool's complexity (7 parameters, nested objects, destructive annotation), the description covers the critical workflow, prerequisites, and safety constraints thoroughly. The existence of an output schema covers return values. The main gaps are the undocumented newStakeholderName and consentToAiRead parameters and the potential ambiguity around the 'would_create' path, but the overall context is sufficient for an AI agent to execute the tool safely.

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?

The description explains the semantics of the core workflow parameters (preview, sourceS3Uri, rsaTermsOverride, stakeholderId) and describes the data flow, which compensates considerably for the low schema coverage (29%). However, it leaves consentToAiRead and newStakeholderName unexplained, and the description's statement that it does not create a stakeholder seemingly conflicts with the newStakeholderName parameter, leaving a clear gap.

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 clearly states what the tool does: imports a signed Restricted Stock Purchase/Award Agreement (RSA) from an uploaded PDF and stores it in S3. It explicitly distinguishes it from sibling tools by saying 'USE THIS (not ExtractRsaTermsOcr + CreateCapTableAgreement, and not RecordCapTableInvestment)' and specifies when to use it: 'whenever the user provides or uploads a signed RSA PDF.'

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?

The description provides explicit when-to-use guidance, including the exact condition ('whenever the user provides or uploads a signed RSA PDF') and names the alternatives to avoid. It also explains prerequisites (grantee must already exist) and the mandatory two-step human-in-the-loop flow, including the sequence of steps to call preview and then finalize.

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 toolsInspect
Try in Browser
RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

TDQS

C2.5/5.0
Disambiguation1/5

Multiple tool pairs are nearly identical (formation_extract_cap_table / formation_extract_cap_table_ocr; formation_start_formation / formation_create_formation), and several tools lack descriptions, making selection ambiguous. The scale of 202 tools with overlapping summaries (e.g., multiple cap-table summary tools) compounds the confusion.

Naming Consistency3/5

Dominant snake_case `module_verb_noun` pattern, but with notable deviations: `captable_send_safe_for_signature` uses an inconsistent abbreviation, `check_company_name_availability` lacks a module prefix, and `get_list_` vs `list_` prefixes are mixed. Readable but not fully consistent.

Tool Count1/5

202 tools is far beyond any reasonable surface for a single server, even a broad platform. The sheer number overwhelms and makes tool discovery impractical; many tools are peripheral (ads metrics) to the core formation purpose.

Completeness4/5

The domain appears well covered: formation flows, cap-table lifecycle (import, close, simulate), accounting (journal entries, periods, schedules), cards, documents, and transactions all have CRUD or lifecycle operations. Minor gaps exist (e.g., no card deletion, no counterparty creation), but they are unlikely to cause dead ends.

Resources