La mayoría de las integraciones de rastreadores de tareas son envoltorios CRUD: le dan a un agente create_task,
update_task, delete_task y esperan que el prompt lo mantenga honesto. Esta hace lo contrario.
Expone doce herramientas específicas, y cada una rechaza los movimientos que romperían el proceso:
Backlog → Queue → Design → Build → Review → [human] → Done
↕ ↕
Your Call (+ independent review of every task in Review)Backlog y Done son territorio humano. Triage en un extremo, aprobación en el otro.
No hay argumento para advance que llegue a Done — a un agente que lo intente se le dice
solo un humano mueve una tarea a Done después de la revisión.
Queue → Design → Build → Review es el bucle del agente. Reclama una tarea, escribe una especificación para salir
de Design, produce un worklog y un sha de evidencia para salir de Build.
Your Call es la rama lateral para cuando un agente necesita una decisión que no debería tomar
solo. Mantiene su asignación y su contexto; el humano responde en la tarjeta.
Las compuertas son barandillas para los agentes, no un límite de seguridad — el límite real es el token de API con alcance que Vikunja emite. Ver SECURITY.md.
Related MCP server: Accordo
Un agente autónomo que se deja corriendo contra una API de tareas simple se desvía de maneras que son individualmente razonables y colectivamente inútiles: marca su propio trabajo como hecho, comienza lo siguiente antes de terminar esto, "arregla" un error eliminando el test, y el único registro de todo ello es un registro de chat que se desplazó hace tres horas.
Nada de eso se arregla con un prompt más largo. El prompt es un consejo; la llamada a la herramienta es el punto de decisión. Así que el proceso se aplica donde ocurre la decisión:
En lugar de esperar que el agente… | …la herramienta rechaza |
no califique su propio trabajo |
|
escriba un plan antes de codificar |
|
diga qué hizo y dónde |
|
trabaje en una cosa a la vez |
|
escalar en lugar de adivinar |
|
deje un rastro que un humano pueda auditar | cada transición escribe un comentario marcado en la tarjeta |
Lo que obtienes es un tablero donde cada tarjeta lleva su propia historia — la reclamación, el plan, el trabajo, el veredicto independiente — en el orden en que ocurrió.
Una tarjeta que ha recorrido todo el bucle. Nada aquí fue escrito por un humano: los marcadores, las etiquetas y la etapa son lo que las herramientas escribieron mientras los agentes la movían.
Leyendo de arriba a abajo, eso es claim → advance(to="build", spec=…) → advance(to="review", worklog=…, evidence=…) → el review_task(verdict="approve", report=…) de un agente diferente.
La etiqueta reviewed es lo que dejó el veredicto; la tarjeta ahora está en Review esperando que
un humano la apruebe. Cada tarea recibe esa revisión, no solo las correcciones de errores — solo un
contenedor epic está exento, porque su código vive en sus hijos.
Y cuando el agente se encuentra con una decisión que no le corresponde tomar, estaciona la tarjeta en lugar de adivinar:
La tarjeta conserva su asignado, así que vuelve al mismo agente cuando respondas. Configura
VIKUNJA_NOTIFY_WEBHOOK y también recibes un ping con forma de Slack con un enlace profundo, de modo que
estacionar una pregunta no significa esperar a que alguien note un tablero.
1. Instalar — no se necesita clonar, uvx lo ejecuta directamente desde el repositorio:
uvx --from git+https://github.com/ufna/vikunja-mcp@stable vikunja-mcp --version2. Crear el tablero. Con un token de administrador, esto crea el proyecto si falta y
reconcilia las siete columnas canónicas (también migra las columnas Todo/Doing de un tablero Vikunja
predeterminado, e imprime fragmentos de configuración listos para confirmar):
VIKUNJA_TOKEN=<admin token> uvx --from git+https://github.com/ufna/vikunja-mcp@stable \
vikunja-mcp setup --project "My Project" --share agent-bot:write --url https://vikunja.example.com3. Apuntar el repositorio a él. Confirma .vikunja-mcp.toml; mantén el token fuera de él:
[tracker]
url = "https://vikunja.example.com"
project_id = 12
wip_limit = 3 # how many Design/Build tasks one token may claim into at once
language = "en" # "en" | "ru" — what language cards are written in# .vikunja-mcp.env — same directory, gitignored, NEVER committed
VIKUNJA_TOKEN=tk_xxxxxxxxxxxx4. Registrar el servidor con Claude Code (.mcp.json) o opencode
(opencode.json). Ambos se suscriben a la rama stable en movimiento, por lo que los lanzamientos se implementan en el
próximo inicio de sesión sin necesidad de actualizaciones por repositorio:
{ "mcpServers": { "tracker": {
"command": "uvx",
"args": ["--refresh-package", "vikunja-mcp",
"--from", "git+https://github.com/ufna/vikunja-mcp@stable", "vikunja-mcp"]
} } }{ "$schema": "https://opencode.ai/config.json", "mcp": { "tracker": {
"type": "local",
"command": ["uvx", "--refresh-package", "vikunja-mcp",
"--from", "git+https://github.com/ufna/vikunja-mcp@stable", "vikunja-mcp"],
"enabled": true
} } }5. Enseñar al agente el proceso — vikunja-mcp install-skill instala la habilidad de tracker empaquetada
(disciplina de cola, cuándo escalar, qué debe un worklog a un revisor) tanto para Claude Code como para opencode.
Para Claude Code también aprovisiona un hook condicional SessionStart para que dentro de un proyecto configurado
con tracker, un /loop simple drene la cola en lugar de recurrir al predeterminado genérico "no empieces a trabajar
por tu cuenta". Fuera de ese proyecto, el hook no emite nada.
Luego ejecuta el bucle. /loop 10m para trabajo desatendido, /loop simple cuando estás mirando.
Tool | Gate / behavior |
| Una cosa, en orden: tu tarjeta activa de Design/Build (incluida una devuelta desde Your Call), luego una tarjeta de Queue ya asignada a ti, luego una tarjeta en Review esperando un veredicto independiente, luego la tarjeta libre superior de Queue. Nunca ofrece Backlog, una tarjeta con etiqueta |
| Queue → Design solamente, y solo bajo el límite de WIP. Asignar-luego-verificar: te asigna, relee la tarjeta y se retira si otro ganó la misma ventana. |
| El expediente: descripción, etapa, asignados, etiquetas, adjuntos, hilo de comentarios completo. |
| Una nota de progreso en la tarjeta. |
|
|
|
|
| Design/Build → Your Call, manteniendo tu asignación. Publica la pregunta y, si está configurado, envía un ping a un webhook. |
| Para bloqueadores externos (sin acceso, falta una dependencia, el servicio de otro está caído). Te desasigna, agrega |
| Divide tu propia tarea sobredimensionada en ≥2 subtareas de Queue vinculadas al padre; el padre se convierte en un contenedor |
| Registra un hallazgo fuera de alcance en Backlog para triage humano — nunca directamente en Queue. Opcionalmente vinculado a la tarjeta donde lo encontraste. |
| Adjunta un archivo local — típicamente una captura de pantalla del trabajo terminado — para que el revisor pueda ver el resultado. Se registra a sí mismo en la tarjeta. |
| Devuelve una ruta para leer, no base64, para que una captura de pantalla nunca infle el contexto del agente. |
Tres comandos completan el bucle; ninguno habla MCP, y el SDK se importa de forma perezosa para que no paguen por ello.
vikunja-mcp claimable — una línea JSON que responde "¿hay trabajo reclamable para este token ahora mismo?",
salida 0 si la verificación se ejecutó. Llama al next_task() real, por lo que no puede desviarse de las compuertas,
y es de solo lectura por contrato. Diseñado para un supervisor que de otro modo iniciaría una sesión de agente de pago
en cada tick de sondeo solo para descubrir que no había nada que hacer.
vikunja-mcp workspace <id> — un worktree de git por tarea en una rama desechable task/<id>, para que varios agentes puedan drenar la cola en paralelo sin pelearse por un único checkout. --release hace push y limpia; --gc recolecta huérfanos y hace fast-forward de tu checkout principal. Su regla de seguridad es una línea: push OK → eliminar, push FAIL → conservar. El trabajo sucio, sin push o inalcanzable se reporta, nunca se destruye. (Una excepción real, documentada en lugar de ocultada: los archivos ignorados por git son invisibles para la comprobación de suciedad. Saca las capturas de pantalla del worktree antes de liberarlo — ver el dossier).
vikunja-mcp setup / install-skill — reconciliación idempotente del tablero, y la instalación de la skill orientada al agente descrita anteriormente. Ambos son seguros de re-ejecutar; el servidor MCP también auto-repara la skill instalada al iniciar, por lo que un stable en movimiento la actualiza automáticamente.
Cuatro capas, prioridad más alta primero:
Entorno — VIKUNJA_URL, VIKUNJA_TOKEN, VIKUNJA_PROJECT_ID, VIKUNJA_NOTIFY_WEBHOOK
.vikunja-mcp.env — archivo KEY=VALUE local al repositorio junto al toml, ignorado por git. El token por proyecto para una máquina que trabaja en varios repos.
.vikunja-mcp.toml — commiteado, encontrado subiendo desde el cwd. Seguro de commitear porque no contiene secretos.
~/.config/vikunja-mcp/env — el lugar habitual para un VIKUNJA_TOKEN personal (chmod 600).
Dos reglas hacen que esa división importe, y van en direcciones opuestas:
Un secreto nunca se lee del toml. Ni el token, ni la URL del webhook. Así que el archivo commiteado no puede filtrar uno ni por accidente.
La política del equipo nunca se lee del entorno. wip_limit, require_review_independence y language son solo del toml, porque describen cómo funciona el proyecto, no en qué máquina estás. Sin definir, wip_limit es 3 — no "ilimitado"; wip_limit = 0 es un error de configuración, porque "sin límite" deliberadamente no es expresable. Sin definir, language es "en", y un valor no reconocido es un error de configuración por la misma razón.
worktree_root se encuentra en el lado de la máquina de esa línea, así que ahí el entorno gana.
language gobierna más que la salida propia de la herramienta. La especificación, el worklog y el informe de revisión son la mayor parte del texto de una tarjeta y la herramienta no los escribe — el agente lo hace — así que el valor también viaja en cada respuesta de next_task, y el libro de reglas empaquetado le dice al agente que escriba en él. Lo que nunca toca son los marcadores de comentario ([worklog], [review], …): dos de ellos se comparan con startswith para decidir si una tarjeta se ofrece para revisión, por lo que están congelados en todos los idiomas.
Razonamiento completo, incluyendo por qué el límite de WIP controla una transición en lugar de vigilar un recuento: docs/dossier/config.md.
Los consumidores se suscriben a la rama stable en movimiento. Cada push verde a main incrementa automáticamente la versión de parche, etiqueta vX.Y.Z, y mueve stable a ella — así una corrección llega a cada repositorio consumidor en su próximo inicio de sesión, sin bots de PR y sin incrementos de versión por repositorio. Las etiquetas inmutables siguen siendo el historial y los puntos de reversión:
git branch -f stable vX.Y.Z && git push -f origin stable # rollback to a known-good tagLos incrementos menores y mayores son un commit editado a mano; CI reanuda el auto-parcheo desde la nueva línea base. docs/dossier/releases.md tiene el análisis de carrera detrás del push atómico y el canal solo hacia adelante.
uv sync
uv run ruff check .
uv run pytest tests/unit -qLas pruebas de integración se ejecutan contra un contenedor Vikunja real y se omiten a sí mismas sin VIKUNJA_TEST_URL — la receta está en CONTRIBUTING.md, junto con las reglas de la casa que son menos obvias de lo que parecen (por qué la longitud de línea es dos números, y por qué un barrido de mutaciones sin una ronda de control no mide nada).
docs/ — las reglas viven en CLAUDE.md; la evidencia vive en nueve dossiers, uno por subsistema. Si estás a punto de cambiar una guardia, su dossier es donde está escrita la medición que la puso allí.
MIT — ver LICENSE.
Продвинуть СВОЮ задачу: to='build' требует spec (подход/дизайн); to='review' требует worklog + evidence (коммит/PR/вывод верификации). Перехода в Done нет — Done ставит человек после ревью.
| Name | Required | Description | Default |
|---|---|---|---|
| to | Yes | ||
| spec | No | ||
| task_id | Yes | ||
| worklog | No | ||
| evidence | No |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Discloses that 'Done' is not set by this tool and that specific parameters are required per transition. However, no annotations are present, and the description lacks details on side effects, permissions, or response behavior.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Three sentences, front-loaded with purpose and specific conditions. No redundant information, though could be slightly more structured.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool's complexity (5 params, 2 required) and lack of output schema, the description covers the two main use cases and their requirements. Could mention if other 'to' values exist or indicate return value.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Adds meaning beyond input schema by explaining that 'to' values 'build' and 'review' require 'spec' and 'worklog'+'evidence' respectively. Schema has 0% description coverage, so description compensates for key parameters, though not all 5 parameters are explained.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
Description clearly states the tool advances a task to 'build' or 'review' states, with specific parameter requirements. It distinguishes from siblings like 'claim' or 'decompose' by focusing on state transitions.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
Explicitly states when to use (for 'build' and 'review' transitions) and when not to use ('no transition to Done'). Provides conditions for each transition, though no explicit comparison to other sibling tools.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Застрял и нужен человек (решение/вводные): вопрос уйдёт комментом, задача — в колонку 'Call to Human', assignee сохранится. Это НЕ ревью и НЕ внешняя блокировка.
| Name | Required | Description | Default |
|---|---|---|---|
| task_id | Yes | ||
| question | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the full burden. It transparently discloses key behaviors: question becomes a comment, task moves to a specific column, assignee is preserved. It also clarifies exclusions (not a review, not an external blocker). This is solid for a simple tool.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is extremely concise, using only two sentences to convey purpose, effects, and exclusions. Every sentence adds value with no redundancy. Front-loaded with main action.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given no annotations, output schema, or complex parameters, the description covers the essential behavioral context and flow. It could mention prerequisites (e.g., task existence) but is largely complete for the tool's simplicity.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 0%, so description must compensate. It implicitly maps parameters to their roles: task_id (task to move) and question (comment content). However, it does not provide explicit parameter descriptions or constraints, relying on context. Adds value but insufficiently detailed.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool's purpose: to call a human when stuck, moving the task to 'Call to Human' column and posting the question as a comment. It also distinguishes itself by stating what it is NOT (review or external blocker), aiding differentiation from siblings.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description implies when to use ('stuck and need a human') and what it is not, but does not explicitly compare to sibling tools or provide when-not-to-use guidance. Usage context is clear but lacks explicit alternatives.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Взять задачу из Queue: назначает тебя и переносит в Design. Откажет, если задача не в Queue, занята или проиграна гонка (тогда next_task).
| Name | Required | Description | Default |
|---|---|---|---|
| task_id | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Without annotations, the description conveys key behaviors: it assigns the user, moves the task, and lists failure conditions. This is comprehensive for a mutation tool.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is extremely concise, with two sentences that convey the main action, constraints, and alternatives. Every word adds value.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a simple one-parameter tool with no output schema, the description covers purpose, side effects, error handling, and references to sibling tools, making it contextually complete.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The description does not explicitly define the parameter 'task_id', but the context of claiming a task makes its purpose obvious. With 0% schema coverage, more explicit parameter description would be beneficial.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool claims a task from Queue, assigns it to the user, and moves it to Design. It specifies the resource and action, distinguishing it from sibling tools.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description explicitly states when to use (take task from Queue) and when not (if not in Queue, already taken, or race condition). It provides the alternative 'next_task' for failure cases.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Заметка о ходе работы: находки, решения ('выбрал X вместо Y потому что Z').
| Name | Required | Description | Default |
|---|---|---|---|
| text | Yes | ||
| task_id | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries full transparency burden. It indicates a non-destructive action (adding a note), but does not disclose whether the comment is appended, overwritten, or has any side effects. No rate limits or permissions are mentioned.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is very short and front-loaded, but it omits critical parameter information. While concise, it fails to be sufficiently informative, reducing its practical value.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given no output schema and zero schema description coverage, the description is severely incomplete. It does not explain input expectations, return values, or behavior, leaving an agent with significant ambiguity.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 0%, yet the description provides no explanation of the required parameters (task_id and text). An agent cannot determine what task_id refers to or what form text should take without additional context.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool is for adding notes on progress, findings, and decisions, which aligns with the verb 'comment'. It provides specific examples of content ('chose X instead of Y because Z'), making it distinct from sibling tools like 'advance' or 'claim'.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
No explicit guidance is given on when to use this tool versus alternatives. The description implies it is for recording observations, but does not specify when not to use it or mention any prerequisites.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Разбить СВОЮ большую задачу (>~полдня работы) на >=2 подзадачи: [{'title': ..., 'description'?: ..., 'priority'?: 0-5}]. Подзадачи встают в Queue с relation на родителя; родитель уходит в Backlog с label 'epic'.
| Name | Required | Description | Default |
|---|---|---|---|
| task_id | Yes | ||
| subtasks | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the full burden. It explains that subtasks go into the Queue with a relation to the parent, and the parent moves to Backlog with an 'epic' label. This provides useful behavioral context beyond the schema.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is extremely concise and front-loaded, stating the action and conditions immediately. Every sentence adds value, with no wasted words.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given there is no output schema and only two parameters, the description fully explains what the tool does, what inputs are expected, and what side effects occur (parent/child task states). It is complete for this tool's complexity.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 0%, so the description must compensate. It details the subtask format: title, optional description, and optional priority (0-5). This adds meaning to the otherwise generic 'additionalProperties: true' array items.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool breaks a large task into subtasks, specifying that the task must be 'YOUR large task' (>~half day) and that subtasks must be at least two. This clearly differentiates it from sibling tools like get_task or next_task.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description implies when to use: for tasks that are large (more than about half a day) and need to be broken down. However, it does not explicitly state when not to use or provide alternatives, leaving some ambiguity.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Досье задачи: описание, стадия, assignees, лейблы и все комментарии.
| Name | Required | Description | Default |
|---|---|---|---|
| task_id | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations provided, so description carries full burden. It lists the returned fields but does not disclose whether the operation is read-only (though implied) or any side effects. Provides basic behavioral context.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
A single sentence that is front-loaded and contains no unnecessary words. Every part of the description adds value.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a simple get tool with one parameter and no output schema, the description adequately lists what is returned. Could mention that it does not modify data, but overall reasonable.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 0% and the description does not mention the task_id parameter at all. It fails to add meaning beyond the schema.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states it retrieves a task dossier including description, stage, assignees, labels, and all comments. This distinguishes it from sibling tools which are mutation operations (comment, advance, claim, etc.).
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance on when to use this tool versus alternatives. The description only states what it does, not when it is appropriate or when another tool might be better.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Что делать дальше: сначала возвращает ТВОЮ активную задачу (Design/Build, в т.ч. вернувшуюся из Call to Human), иначе — верхнюю свободную из Queue. Backlog и blocked не выдаёт. Одна задача за раз.
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description fully carries the behavioral disclosure burden. It reveals that the tool returns one task at a time, does not give backlog or blocked tasks, and prioritizes the user's active task. This addresses all key behavioral aspects for a read-heavy tool.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single, well-structured sentence that front-loads the main verb and resource. It covers priority logic, exclusions, and limitation without any redundant or unnecessary text.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool's simplicity (no parameters, no output schema), the description is complete. It explains the full behavior required for an agent to use it correctly, including prioritization, exclusions, and the one-task-per-call limit.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The tool has no parameters, so the input schema is empty. The description adds all meaningful context by explaining what the tool actually does, which is entirely beyond the schema. This effectively compensates for the lack of parameters.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description explicitly states it returns the user's active task or the top free task from the queue, and excludes backlog and blocked tasks. This is a specific verb (returns) and resource (task), and it distinguishes itself from siblings like get_task (which retrieves a specific task) and claim (which assigns tasks).
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description clearly indicates when to use the tool: when determining the next task to work on. It explains the priority logic and exclusions. However, it does not explicitly compare to siblings or state when not to use it, which is a minor gap for a score of 5.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Вернуть задачу из-за ВНЕШНЕЙ блокировки (нет доступа/зависимость/чужой сервис): снимает тебя, ставит label 'blocked', уносит в Backlog на ре-триаж человеком.
| Name | Required | Description | Default |
|---|---|---|---|
| reason | Yes | ||
| task_id | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description fully discloses side effects: unassigns user, sets label, moves task to backlog. Clear and honest.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Single sentence, front-loaded with purpose, efficient no waste.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Covers the tool's effect and context well for its simplicity, but omits prerequisites (e.g., task assignment status) and error conditions. Adequate for a basic tool.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 0% (no property descriptions). Description does not elaborate on 'task_id' or 'reason' beyond the tool's context, leaving meaning implicit.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
Description clearly states the tool returns a task due to external blocking, with specific actions (removes assignee, sets label 'blocked', moves to backlog). Distinguishes from siblings like claim, advance, etc.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
Explicitly specifies when to use (external blocking), but does not mention when not to use or alternatives like comment or decompose.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
v0.1.0advancecall_humanclaimcommentdecomposeget_tasknext_taskreturn_taskScored across 8 tools
Each tool has a distinct purpose: advance moves stages, call_human asks for help, claim assigns tasks, comment documents progress, decompose splits tasks, get_task retrieves details, next_task suggests what to do next, and return_task handles blocking issues. No two tools overlap in functionality, making it easy for an agent to select the correct one.
Tool names mix conventions: some are single verbs (advance, claim, comment, decompose), others are verb+noun with underscore (call_human, get_task, return_task), and one is adjective+noun (next_task). While all are lowercase and readable, the lack of a uniform pattern reduces predictability.
With 8 tools, the server is well-scoped for the domain of managing task workflow from queue to completion. Each tool serves a clear role without unnecessary bulk, and the count comfortably fits the typical range for a focused MCP server.
The tools cover core workflow actions (claim, advance, return, get, next, comment, call_human, decompose) but lack basic CRUD operations like creating, updating, or deleting tasks directly. This can force agents into workarounds if new tasks are needed or details must be edited.
Work management where AI agents are first-class members: tasks, projects, memory over hosted MCP
Open-source Zapier/n8n alternative as an MCP server: agents build, run and debug your workflows.
Task management your AI agents can actually run. One line becomes a context-ready task over MCP.
MCP Server for an Agent Task Marketplace
