Skip to main content
Glama

Claim issue

claim_issue

Toma una issue para indicar que la estás trabajando AHORA (lock blando, distinto del assignee). Setea agentWorkingBy = el usuario de la key y agentWorkingSince = ahora. FALLA (409) si ya la está trabajando OTRO agente o si tiene bloqueadoras sin resolver (blocked_by en un estado que no es completed, canceled ni desbloqueante, como In Review por defecto): el error las nombra con su estado. La UI y otros agentes (get_issue) lo ven al instante. Libérala con release_issue. Rechaza (409) una issue en estado terminal (completed/canceled): reábrela antes con change_issue_state. 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[].

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": {
      "id": "<id>"
    },
    "name": "claim_issue"
  }
}

Input Schema

NameRequiredDescriptionDefault
idYesAdmite 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.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.5/5.0
Behavior5/5

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

Annotations only declare readOnlyHint=false, idempotentHint=false, destructiveHint=false; the description goes far beyond by disclosing the 409 failure modes (another agent holds the lock, unresolved blocked_by, terminal state), that the error names the blocking issues with their states, and that the lock is immediately visible to the UI and other agents. It also explains the additive agentLifecycle/agentCloseState/agentGuidance payloads the caller should expect.

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 and its failure conditions are front-loaded, which is good, but the second half expands into a long enumeration of agentLifecycle phases, flags, and transition fields that reads like documentation for the returned payload rather than for invoking this tool. Much of it is useful context, yet it is dense and could be compressed substantially.

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 mutating lock tool with no output schema, the description covers what the call does, the preconditions, the failure semantics, how to undo, and the shape of the accompanying lifecycle/guidance data an agent must respect. Nothing an agent needs in order to call it correctly appears to be missing.

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?

There is only one parameter and the schema description already covers it fully (UUID or TEAM-123, case-insensitive, UUID required on cross-workspace ambiguity). The description never mentions the id argument, adding no meaning beyond the schema, so the baseline of 3 for high coverage applies.

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 + resource and defines the exact semantics: a soft lock that sets agentWorkingBy/agentWorkingSince, explicitly distinct from the assignee. It also names the sibling that undoes it (release_issue) and the one needed for terminal issues (change_issue_state), so an agent can tell it apart from siblings without opening a 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?

Gives explicit when-to-use (claim before working now), when-not/alternative paths (next_ready_issue for queued work, release_issue to free, change_issue_state to reopen a closed issue), and the exact blocking conditions that produce a 409. It also covers precedence rules for conflicting guidance (team overrides workspace).

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