Skip to main content
Glama

Create or update issue

save_issue
Destructive

Crea una issue (numeración TEAM-N atómica) o actualiza una existente si se pasa id. Al CREAR admite issue completa en un call: description (markdown), agentContext (markdown: contexto del agente — archivos relevantes, notas), definitionOfDone y verifyCommand (la Definition of Ready: qué es 'hecho' y el comando que verifica la issue — rellenarlos hace la DoR completa), assigneeId, projectId, milestoneId, dueDate (fecha de vencimiento, epoch ms), parentId (sub-issue) y labelIds. milestoneId mete la issue en un milestone del MISMO proyecto (null lo quita). productId ENTREGA una tarea de una iniciativa a un proyecto producto del workspace (el repositorio donde se implementa; uno solo: si toca dos, pártela) y productMilestoneId la mete en un milestone de ESE producto; cambiar el producto limpia su milestone salvo que lo mandes en la misma llamada. Quien solo escribe en el producto puede cambiar productMilestoneId, no el contenido. Crea milestones con save_milestone. OJO: cambiar projectId borra el milestone salvo que mandes milestoneId en la misma llamada. En UPDATE: agentContext/definitionOfDone/verifyCommand editan esos campos; dueDate fija/limpia (null) el vencimiento; addLabelIds/removeLabelIds asignan o quitan labels. agentReady marca/desmarca la issue como 'lista para agente' (la cola de next_ready_issue) sin cambiar su estado. Usa list_workflow_states/list_labels/list_milestones/list_members/list_custom_fields para los IDs. En UPDATE, stateId mueve la issue igual que change_issue_state (mismos sellos, lock y agentReady); un stateId inválido falla sin aplicar nada. Si OTRO agente tiene un lock vigente sobre la issue, el cambio se aplica igualmente y la respuesta trae warnings. Al CREAR admite workspaceId (dónde nace la issue; sin él, el de la credencial) y la respuesta dice en qué workspace quedó. En UPDATE no hace falta: sale de la propia issue.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "save_issue"
  }
}

Input Schema

NameRequiredDescriptionDefault
idNoAdmite el UUID de la issue o su identificador legible (TEAM-123, el que se ve en la app), sin distinguir mayúsculas. Si ese identificador existiera en varios de tus workspaces hay que pasar el UUID.
titleNo
teamIdNo
dueDateNo
stateIdNo
estimateNo
labelIdsNo
parentIdNo
priorityNo
productIdNo
projectIdNo
agentReadyNo
assigneeIdNo
addLabelIdsNo
descriptionNo
milestoneIdNo
workspaceIdNo
agentContextNo
customFieldsNo
verifyCommandNo
removeLabelIdsNo
definitionOfDoneNo
productMilestoneIdNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A3.9/5.0
Behavior3/5

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

Annotations already cover the safety profile (destructiveHint=true, not idempotent, closed-world), and the description adds real value beyond them: changing projectId wipes the milestone unless milestoneId is sent in the same call, changing productId clears its product milestone, an invalid stateId fails atomically with nothing applied, and a foreign agent lock still allows the change but returns `warnings`. These are meaningful side-effect disclosures. However it never states the permissions model implied by 'whoever only writes in the product can change productMilestoneId', nor what is destroyed on overwrite of description/agentContext, so it does not fully cover the mutation surface.

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

Conciseness3/5

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

Front-loaded with the create/update split, which is correct, but the body is a dense multi-clause paragraph that interleaves create rules, update rules, cascade warnings and lock behaviour without visual separation. Nearly every clause carries information, yet splitting the update-mode and cascade notes into distinct sentences would make it far easier to parse.

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?

For a 23-parameter, no-output-schema mutation tool the definition covers a great deal, but it never states which fields are required for creation, leaves title/priority/estimate/customFields unexplained, and only hints at the response shape (`workspace`, `warnings`). An agent could still call it, but would be guessing on several high-impact parameters.

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 only 4% schema description coverage across 23 parameters, the description must compensate and largely does: it defines create-only fields (productId, productMilestoneId, workspaceId, parentId, dueDate as epoch ms), update-only fields (addLabelIds, removeLabelIds, agentReady, stateId), explicit null-clears semantics for dueDate/milestoneId, and cascade rules on project/product change. It omits meaning for title, teamId, estimate, priority and customFields, which are left to the bare 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 pair and explicitly splits the two modes: create (with atomic TEAM-N numbering) vs update when an id is supplied. An agent can tell instantly what this tool does and how it differs from change_issue_state or save_milestone, both of which are named.

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?

Gives concrete routing guidance: use list_workflow_states/list_labels/list_milestones/list_members/list_custom_fields to obtain IDs, use save_milestone to create milestones, and note that stateId in update behaves identically to change_issue_state. It does not explicitly say when NOT to use it (e.g. bulk operations or transitions requiring the dedicated state tool), so a 4 rather than a 5.

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.

Resources