Skip to main content
Glama

Lovie Company Formation

Capture What Was Said

fundraising_capture_what_was_said

Record what the founder actually said about an existing investor, against the disclosure scope in force at the time. A sentence that went further is flagged and kept, never deleted — the founder needs to see it while it can still be corrected.

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": "fundraising_capture_what_was_said"
  }
}

Input Schema

NameRequiredDescriptionDefault
saidNo
companyIdYesUUID value wrapper.
occurredAtNo
meetingTouchIdNoUUID value wrapper.
relationshipIdNoUUID value wrapper.

Output Schema

NameRequiredDescriptionDefault
captureNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

B3.4/5.0
Behavior4/5

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

Annotations already declare destructiveHint=false and openWorldHint=false, and the description adds meaningful behavioral context: statements exceeding the disclosure scope are flagged but retained, never deleted, and surfaced to the founder for correction. That flag-and-keep semantics is valuable beyond the structured fields, though auth requirements and the flagging trigger mechanics are not stated.

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?

Two tightly written sentences with the guardrail behavior front-loaded after the core action. No filler, though it could have used one clause to name the alternative tool.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

An output schema exists so return-value explanation is unnecessary, and the behavioral guardrail is well covered. However, for a five-parameter nested-object mutation tool, the complete absence of parameter guidance leaves the definition only partially complete.

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?

The description never references any of the five parameters (said, companyId, occurredAt, meetingTouchId, relationshipId). With only 60% schema description coverage and nested UUID wrappers, the description does not compensate for the unexplained fields such as occurredAt and the ID linkages.

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 description names a specific verb ('Record') and resource ('what the founder actually said about an existing investor') with a clear scope constraint ('against the disclosure scope in force at the time'). It is distinct from generic recording tools, though it does not explicitly contrast with siblings like record_touch or ingest_chat_evidence.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Usage is implied by the purpose (capturing founder statements about an investor), but there is no explicit when-to-use/when-not guidance and no named alternative among the many fundraising siblings. The agent must infer when this is preferred over record_touch or ingest_chat_evidence.

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.