Skip to main content
Glama

Corply — Start and run your company

by io.github.corply-dev
OverviewDiscussionsAdmin

Prepare a signing bundle

request_signature

Signatures come before payment. Request signatures for the immutable current revision, then request payment only after all required signatures are recorded. For Delaware C-corps, phase-aware and idempotent: before Delaware acceptance it prepares each founder's one filing-stage bundle. The incorporator's bundle includes the Certificate of Incorporation; every founder's bundle includes the narrow Founder Formation Authorization for the enumerated standard post-acceptance records. After acceptance, standard-v1 records are executed from that stored authorization and must never become a second human signature request. For Delaware, only a legacy formation that predates the authorization can return a post-acceptance signing bundle. Once an authorized founder's RSPA is fully executed and establishes the stock-purchase date, Corply prepares and executes that founder's 83(b) automatically from the same stored authority. Automatically prepares every required signer's current bundle and emails each signer the signature request, including cofounders. Retries reuse the durable outbox and do not resend successful invitations. No separate invite authorization is needed. Report signerInvitations deliveryState; sent means transport accepted, not inbox delivery. Returns only the caller's private signing bundle and review links. Open reviewUrl when possible and show a Markdown link labeled Review documents. Help the founder review before asking for fresh signature consent with the complete authorizationDisclosure and confirmed legal name. If they prefer web signing use webSignUrl. Preparing and emailing documents never signs them. Prerequisite: authenticated active company access plus every prerequisite stated above. Canonicality: invokes the shared backend action; trust the returned actual_tool_output and context_engineering instead of adding a state-recovery call. Idempotency: obey the tool-specific retry key or guarantee; if none is stated, inspect refreshed state before retrying. Confirmation boundary: no additional confirmation is needed for this read, reversible save, explicit fact/evidence record, link preparation, plan refresh, or action pre-authorized by a standing founder-configured policy.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
formationIdYes
_corply_contextNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • removedInput schema / properties / _corply_context / description
      Removed value: -"Echo context_engineering.context_session from the prior Corply result."
  2. Changed1 schema field changed
    • addedInput schema / properties / _corply_context
      Added value: +{
+  "additionalProperties": false,
+  "dependentRequired": {
+    "receipt": [
+      "id"
+    ]
+  },
+  "description": "Echo context_engineering.context_session from the prior Corply result.",
+  "properties": {
+    "id": {
+      "maxLength": 200,
+      "minLength": 16,
+      "type": "string"
+    },
+    "receipt": {
+      "maxLength": 2048,
+      "minLength": 16,
+      "type": "string"
+    }
+  },
+  "type": "object"
+}
  3. First observed

TDQS

A3.7/5.0
Behavior5/5

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

Beyond the annotations (write, non-destructive, open-world), the description discloses a great deal: idempotent and phase-aware behavior, retries reusing a durable outbox without resending successful invitations, deliveryState semantics ('sent' = transport accepted, not inbox delivery), automatic 83(b) execution from stored authority, and that only the caller's private bundle is returned. This adds substantial behavioral context the annotations cannot convey.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness2/5

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

The definition is heavily bloated: generic boilerplate about Canonicality, Idempotency, and the Confirmation boundary consumes several sentences that add no tool-specific value, and domain narrative (Delaware phases, 83(b), RSPA) is interleaved with invocation mechanics. The first sentence is a good hook, but the rest is far longer than the task requires.

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, stateful signing/preparation tool with no output schema, the description covers return content (caller's bundle and review links), delivery-state semantics, retry behavior, and prerequisites, which is strong. The gap is that the parameters and the required _corply_context object are never explained, leaving invocation inputs under-specified.

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

Parameters2/5

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

Schema description coverage is 0% and the description never explains the two parameters. formationId is not described at all, and the nested _corply_context object (id/receipt) is never mentioned, so an agent gets no guidance on what to supply or how the context object is used.

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?

The opening lines state a specific action (request signatures for the immutable current revision) and the ordering rule versus payment, and the line 'Preparing and emailing documents never signs them' implicitly separates it from sign_bundle. However, the core purpose is embedded in a wall of domain-specific and generic boilerplate, and no sibling tool is named explicitly, so the agent must work to isolate the essence.

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?

There is clear sequencing context: signatures before payment, request only after required signatures are recorded, and the Delaware phase-aware behavior (pre- vs post-acceptance). The confirmation-boundary sentence also tells the agent no extra confirmation is needed. It stops short of naming alternatives like sign_bundle or request_governed_signatures, so it is not a 5.

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

All Corply — Start and run your company toolsInspect
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.

Resources