Corpus Law

Validate and hand off a formation draft

formation.handoff

Read-onlyIdempotent

Validate a formation draft and generate the prefilled handoff link on corpuslaw.us. Pass EVERYTHING you have collected (people, address, management, EIN answers, state-specific answers — see formation.requirements for the checklist). The response says exactly what is still missing — keep collecting and call again until COMPLETE, then give the user the link: it opens the formation agent with every detail pre-loaded, so they only review, sign in, and pay. Free; does not consume credits.

Input Schema

TableJSON Schema

Name	Required	Description
`ein`	No	Optional EIN (federal tax ID) add-on, when available — formation.requirements says whether it can currently be sold and at what price. Never quote a remembered EIN price; use the one that call returns. Set wanted=true/false once the user decides. NEVER include a Social Security Number anywhere — the founder types it into a secure panel on corpuslaw.us, never in chat.
`state`	Yes	Two-letter US state code, e.g. 'MS', 'WY', 'DE'.
`parties`	No	The people. LLC: at least one 'member' and an 'organizer' (same person may hold both roles — pass two entries). Nonprofit: an 'incorporator' and at least 3 'director' entries (plus officers where the state requires them).
`naicsCode`	No	NAICS industry code, 2–6 digits (use formation.lookup_naics to find it).
`nonprofit`	No	Nonprofit-only fields.
`entityType`	Yes	Entity type to form.
`management`	No	LLC management type.
`contactEmail`	No	Founder contact email.
`proposedName`	No	Proposed company name.
`referral_code`	No	Your referral code from account.status, if you have one. The founder saves 25% of the Corpus service fee and the order is credited to your code. Omit it if you do not have one — an absent or unrecognised code changes nothing about the link.
`principalOffice`	No	Principal office address (street, city, state required for a complete draft).
`stateSpecificAnswers`	No	Per-state quirk answers under the EXACT keys shown by formation.requirements (e.g. "would_you_like_to_list_members_managers_on_the_state_record"). Values are strings or booleans.

Output Schema

TableJSON Schema

Name	Required	Description	Default
`text`	Yes	Human-readable tool result (also mirrored in content[].text).
`isError`	No	True when the tool could not complete successfully.

Schema Changelog

Changes observed during successful MCP inspections.

Changed1 schema field changedSep 4, 2026

changedInput schema / properties / ein / description

Previous value: -"Optional $75 EIN (federal tax ID) add-on, when available — formation.requirements says whether it can currently be sold. Set wanted=true/false once the user decides. NEVER include a Social Security Number anywhere — the founder types it into a secure panel on corpuslaw.us, never in chat."New value: +"Optional EIN (federal tax ID) add-on, when available — formation.requirements says whether it can currently be sold and at what price. Never quote a remembered EIN price; use the one that call returns. Set wanted=true/false once the user decides. NEVER include a Social Security Number anywhere — the founder types it into a secure panel on corpuslaw.us, never in chat."

First observedAug 22, 2026

TDQS

A4.7/5.0

Behavior5/5

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

Annotations already indicate readOnly, openWorld, idempotent, and non-destructive behavior. The description adds valuable behavioral detail beyond annotations: the response reports missing items, the generated link preloads details for review/sign-in/payment, and the call is 'Free; does not consume credits.' 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.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Three sentences carry the full operational loop: validate, iterate on missing items, hand off the link. Every sentence earns its place, and the primary action is front-loaded before supporting details.

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 complex 12-parameter tool with nested objects and an output schema, the description is complete: it defines validation, iteration, completion criteria, link behavior, and cost implications. It also references the checklist source, leaving no critical operational gap for an agent to infer.

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 adds meaningful parameter-level guidance by instructing the agent to pass 'EVERYTHING' collected and to consult formation.requirements for the checklist, emphasizing the completeness-driven usage pattern. It does not redefine individual parameters, but it reinforces the aggregate semantics of the payload.

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 states a specific action and resource: 'Validate a formation draft and generate the prefilled handoff link on corpuslaw.us.' It clearly distinguishes this tool from siblings like formation.requirements and law.search by focusing on validation and handoff rather than lookup or legal content.

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 description gives clear usage context: pass everything collected, call repeatedly until COMPLETE, then give the user the link. It explicitly points to formation.requirements for the checklist, but does not explicitly state when not to use this tool versus each sibling; the guidance is clear enough for practical selection.

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

All Corpus Law tools Inspect

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.

Resources

Need Help?