Skip to main content
Glama

Lovie Company Formation

Set Voice Profile

fundraising_set_voice_profile

Record how an investor speaks and writes: the data tier (high, medium, low) the profile rests on, how many sources of each type were read (video, podcast, blog, article, social, thesis, portfolio, debate, background, sector), up to ten top quotes each with its source URL, style traits, tone calibration, signature phrases, topics, pitch strategy and the writing spec (sentence architecture, vocabulary, opening pattern, write like / avoid, rhetorical devices, forbidden patterns, phrases to mirror). A quote without a source URL is refused; every quote is screened for instructions aimed at an agent. Replaces the previous profile. Prefer proposing it with fundraising_propose_change (SET_VOICE_PROFILE).

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>",
      "relationshipId": "<relationshipId>",
      "profile": "<profile>"
    },
    "name": "fundraising_set_voice_profile"
  }
}

Input Schema

NameRequiredDescriptionDefault
profileYes
agentNameNo
companyIdYesUUID value wrapper.
relationshipIdYesUUID value wrapper.

Output Schema

NameRequiredDescriptionDefault
profileNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

A4.3/5.0
Behavior4/5

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

Annotations only declare openWorldHint=false and destructiveHint=false, so the description carries the real weight: it discloses a hard validation rule (a quote without a source URL is refused), prompt-injection screening of every quote, and that the call replaces the previous profile. Remaining gaps are permission/auth requirements and whether the overwrite is recoverable.

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-loaded with the action, and nearly every clause maps to a real schema field rather than filler. The body is one very long catalogue sentence, which is dense to parse, but no obvious padding exists to cut.

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 nested, 4-parameter write with an output schema and thin annotations, the description covers the payload shape, the validation rules, and the overwrite semantics. It does not identify the relationship scope explicitly (that the profile is keyed per relationship) or any follow-up/read path to verify the stored result.

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 description coverage, the description compensates well: it spells out the dataTier levels (high/medium/low), the per-source-type counts (video, podcast, blog, article, social, thesis, portfolio, debate, background, sector), the ten-quote cap with mandatory sourceUrl, and the writing-spec sub-fields. It says nothing about companyId, relationshipId, or agentName, leaving those to the schema.

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?

Opens with a specific verb+resource ('Record how an investor speaks and writes') and enumerates the profile's content precisely enough that an agent knows exactly what artifact this creates. It also distinguishes itself from the sibling that proposes the same payload (fundraising_propose_change with SET_VOICE_PROFILE).

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?

Explicitly routes the agent: 'Prefer proposing it with fundraising_propose_change (SET_VOICE_PROFILE).' That names the alternative and the default path. What is missing is the condition under which direct use is correct (e.g., after approval or when no proposal flow is active).

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.