Skip to main content
Glama

Duvo MCP

by io.github.duvoai

Propose Clarity Landscape Process

proposeClarityLandscapeProcess

Create a manual process in the organization's Process Landscape, either as an unassigned proposal or atomically assigned to an eligible team.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
nameYes
orgIdYes
teamIdNo
parentIdNo
descriptionNoOne short paragraph (1-3 sentences) saying why this process belongs in the landscape. Use only what you saw in the captures. Say what the process is (don't just repeat the name), show proof it really happens, and name where you heard it - be as specific as the captures allow, like "a warehouse lead said so in their interview" or "it came up in two returns recordings". Use only facts from the captures: never make up sources, people, dates, quotes, or numbers, and don't stretch what was said. If you have no real proof the process happens, don't propose it.
materializationModeNoUse "proposal" to record a process the organization plausibly needs, owned by `teamId` for review, WITHOUT creating a real process record. `teamId` is then required. Chat-scoped discovery agents may use proposal mode for their pinned team; direct human and API callers require Manager-or-above authority for that team. A proposal is idempotent: an equivalent live proposal under the same parent is returned untouched rather than duplicated. Defaults to "auto", which materializes a real process when `teamId` is set — except in a landscape-onboarding chat, which may only propose, and so defaults to "proposal".

Schema Changelog

Changes observed during successful MCP inspections. Dates show when Glama detected each change.

  1. Changed1 schema field changed
    • changedInput schema / properties / materializationMode / description
      Previous value: -"Use \"proposal\" to record a process the organization plausibly needs, owned by `teamId` for review, WITHOUT creating a real process record. `teamId` is then required. A proposal is idempotent: an equivalent live proposal under the same parent is returned untouched rather than duplicated. Defaults to \"auto\", which materializes a real process when `teamId` is set — except in a landscape-onboarding chat, which may only propose, and so defaults to \"proposal\"."New value: +"Use \"proposal\" to record a process the organization plausibly needs, owned by `teamId` for review, WITHOUT creating a real process record. `teamId` is then required. Chat-scoped discovery agents may use proposal mode for their pinned team; direct human and API callers require Manager-or-above authority for that team. A proposal is idempotent: an equivalent live proposal under the same parent is returned untouched rather than duplicated. Defaults to \"auto\", which materializes a real process when `teamId` is set — except in a landscape-onboarding chat, which may only propose, and so defaults to \"proposal\"."
  2. Changed2 schema fields changed
    • removedInput schema / properties / materializationMode / default
      Removed value: -"auto"
    • changedInput schema / properties / materializationMode / description
      Previous value: -"Use \"proposal\" to record a process the organization plausibly needs, owned by `teamId` for review, WITHOUT creating a real process record. `teamId` is then required. A proposal is idempotent: an equivalent live proposal under the same parent is returned untouched rather than duplicated. The default \"auto\" materializes a real process when `teamId` is set."New value: +"Use \"proposal\" to record a process the organization plausibly needs, owned by `teamId` for review, WITHOUT creating a real process record. `teamId` is then required. A proposal is idempotent: an equivalent live proposal under the same parent is returned untouched rather than duplicated. Defaults to \"auto\", which materializes a real process when `teamId` is set — except in a landscape-onboarding chat, which may only propose, and so defaults to \"proposal\"."
  3. First observed

TDQS

A3.9/5.0
Behavior4/5

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

All annotation hints are false, so the description carries the full disclosure burden. It discloses the critical behavioral distinction that proposal mode creates no real process record ('WITHOUT creating a real process record'), scopes idempotency to proposals ('an equivalent live proposal... is returned untouched rather than duplicated'), states the Manager-or-above authorization requirement, and reveals context-dependent defaulting (auto vs. proposal depending on caller context). The idempotency qualifier refines rather than contradicts idempotentHint=false, since auto mode creates new records.

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?

The main description is a single verb-first sentence with zero filler. Every phrase earns its place: 'manual' distinguishes from automated processes, 'in the organization's Process Landscape' anchors the resource, and 'either as an unassigned proposal or atomically assigned to an eligible team' compresses the entire mode distinction into one clause.

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?

The two riskiest aspects — choosing proposal vs. auto mode and the role of teamId — are thoroughly covered by the combination of the main description and schema parameter docs, including auth, idempotency, and defaults. But with no output schema, the description never states what the tool returns (created process ID? proposal object?), parentId semantics are absent, and 'eligible team' eligibility criteria are undefined, leaving an agent to guess at failure conditions and result handling.

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

Parameters3/5

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

Schema coverage is 33%, below the 50% threshold where a baseline 3 would suffice, so the description must compensate. The main description's 'unassigned... or atomically assigned' dichotomy maps usefully to teamId, and materializationMode's schema doc explicitly ties teamId to proposal mode ('owned by teamId for review'). The description parameter also has unusually detailed authorship guidance. However, parentId semantics are entirely unexplained, 'eligible team' is left undefined, and name/orgId receive no elaboration beyond field names.

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 states a specific verb+resource ('Create a manual process in the organization's Process Landscape') and immediately disambiguates the tool's dual behavior: unassigned proposal versus atomically assigned creation. It meaningfully narrows scope with 'manual process' among a sibling list containing createClarityProcess, createClarityProcessNode, and createClarityLandscapeNode. It stops short of a 5 because it never names a sibling it is not (e.g., createClarityProcess), leaving some differentiation to inference.

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 materializationMode parameter description provides explicit when-to-use guidance: 'proposal' for plausible-but-unverified processes with teamId required and no real record created, 'auto' to materialize when teamId is set, plus the landscape-onboarding-chat exception that forces proposal mode. It also states caller constraints (chat-scoped discovery agents vs. direct human/API callers requiring Manager-or-above). No explicit comparison to sibling tools like createClarityProcess, so it misses the 'alternatives' component of a 5.

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

All Duvo MCP 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

B3.1/5.0
Disambiguation2/5

Despite detailed descriptions, many tool names are highly ambiguous, with multiple tools covering the same conceptual actions (e.g., acceptClarityCaptureSuggestion vs. acceptClarityTeamAssignmentSuggestion, or the many deleteClarity*Interview tools). The set is so large that distinguishing between, say, listClarityFolders, listClarityProcesses, and listClarityProcessSummaries requires reading deep into descriptions, reducing agent selection accuracy.

Naming Consistency4/5

The naming convention is predominantly verb_noun (e.g., createClarityProcess, listAgents, deleteQueue), and is remarkably consistent across the 316 tools. There are only minor deviations, such as 'fileSuggestedClarityProcesses' (verb + adjective noun) and 'bulkUpdateCasePriority' (where 'bulk' could be seen as a prefix), but overall the pattern holds strongly.

Tool Count1/5

With 316 tools, this server is extremely oversized for any single agent to manage effectively. The massive number of tools suggests poor modularization—many of these tools likely belong in separate, smaller servers focused on specific domains (e.g., Clarity, Pulse, Agent management). The cognitive load for an agent to choose from 316 options is very high, leading to frequent misselection.

Completeness4/5

The tool surface covers an extraordinarily wide range of operations across the Duvo platform: agents, runs, cases, queues, Clarity processes, skills, integrations, notifications, teams, and more. Most resource types have full CRUD and lifecycle management. Notable minor gaps exist (e.g., no tools for managing specific notification batch severities dynamically, and some interview management is missing batch operations), but for the platform's scope, coverage is impressively thorough.

Resources