Skip to main content
Glama

Claim next ready issue

next_ready_issue

Saca de la cola 'lista para agente' la SIGUIENTE issue libre y la RECLAMA atómicamente para ti (agentWorkingBy = tu usuario), de una sola vez y sin carreras con otros agentes. Orden: prioridad (urgente primero) y luego la más antigua. Devuelve la issue ya reclamada (con su contexto) o, si no hay ninguna, { issue: null, reasons, message, nextSteps }: reasons cuenta las issues sin empezar que no salen y por qué (notReady, blocked, noWriteAccess, archivedProject, locked, epics; cada una en su primer motivo). Trabájala y libérala con release_issue al terminar. agentCloseState (stateId, name, instruction) es el estado de cierre que el dueño o un admin del workspace ha configurado para el trabajo de los agentes. agentGuidance (workspace, team, instruction) son las instrucciones fijas que una persona del workspace ha escrito para los agentes (convenciones, qué no tocar, cómo cerrar una issue): síguelas; si la del equipo contradice a la del workspace, manda la del equipo. No es memoria tuya (mem_*): la memoria la escribes tú, la guía una persona. Falta si no hay ninguna. agentLifecycle (solo lectura, aditivo) dice qué puede hacer YA el agente con la issue: phase = queued (nada la frena y next_ready_issue la repartirá: agentReady, sin empezar, sin bloqueos, sin lock vigente, no es épica, proyecto activo y escribible), blocked (bloqueadoras sin resolver), ready (nada la bloquea pero NO está en la cola: no marcada agentReady o ya en curso sin dueño; se toma con claim_issue), in_progress_mine, in_progress_other (la tiene otro agente con lock vigente), review (estado started que no es el primero por position) o closed (completed/canceled); blockers (con unblocksOn: estados que las desbloquean); readiness (dorComplete, missing, whyNotInQueue); lock (by, since, expiresAt, expired, mine); transitions[] (a qué estados puede moverla, con kind, isAgentCloseState, claimsLock, clearsAgentFlags, wip y warnings) y nextSteps[]. workspaceId opcional: el workspace donde operar (list_workspaces los enumera). Sin él se usa el de la credencial. Consume la cola de UN workspace: sin workspaceId no saca trabajo de los demás. projectId acota la cola a un proyecto; si es un PRODUCTO, incluye las tareas que le entregan las iniciativas (el agente de un repositorio coge su trabajo venga de donde venga).

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": "next_ready_issue"
  }
}

Input Schema

NameRequiredDescriptionDefault
projectIdNo
workspaceIdNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.6/5.0
Behavior4/5

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

Annotations only say it is a non-read-only, non-destructive, non-idempotent call; the description goes far beyond that, disclosing atomic claim semantics with no races, the returned payload including the { issue: null, reasons, message, nextSteps } empty case, the reason taxonomy (notReady, blocked, noWriteAccess, archivedProject, locked, epics), and the agentLifecycle/lock/transitions model. The only shortfall is that this behavior is buried in a dense paragraph rather than surfaced up front, but the disclosure itself is thorough.

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?

The core action is front-loaded in the first sentence, but the rest is one monolithic block packing the return payload, guidance model, and the full agentLifecycle phase/reason/transition taxonomy into a single run-on paragraph. The information largely earns its place, yet the lack of structure makes it hard to scan and pushes key details (release_issue, claim_issue routing) into the middle of the block.

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

Completeness5/5

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

For a complex atomic-claim tool with no output schema, the description supplies the return shape including the null-result object and its reason counts, plus agentCloseState, agentGuidance precedence rules (team overrides workspace), and the full agentLifecycle model (phase, blockers with unblocksOn, readiness, lock, transitions with warnings, nextSteps). Nothing an agent needs to interpret the response or act on it correctly is missing.

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

Parameters5/5

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

Schema description coverage is 0%, so the description must carry all meaning and it does: workspaceId is defined as the workspace to operate in, defaults to the credential's workspace, is enumerable via list_workspaces, and notably scopes the queue to a single workspace. projectId is defined as narrowing the queue to a project and, for a PRODUCT, including tasks from initiatives — semantics that are nowhere in 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?

States a specific verb and resource: atomically claims the NEXT free issue from the 'ready for agent' queue for you (agentWorkingBy = your user), plus explicit ordering (priority urgent first, then oldest). It names the sibling it is differentiated from (claim_issue for issues blocked from the queue) so an agent can pick between them without opening either schema.

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

Usage Guidelines5/5

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

Explicit routing is provided: consume from this queue, work it, then free it with release_issue; issues that are 'ready' but not in the queue (not marked agentReady or already started without owner) go through claim_issue, and claim_issue is also named for that case. It also constrains the scope (one workspace's queue, projectId narrowing) so the agent knows which invocation to use.

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