Wiro MCP Server

Official

Overview Schema Source Related Servers Discussions Admin

Update a Wiro agent

update_agent

Change a deployed agent’s name, description, cover, categories, timezone, session mode, models, and slash commands; pass only fields to update, or just the GUID to refresh setup status.

Instructions

Change a deployed agent's name, description, cover or categories, and its settings: timezone (used by scheduled tasks), team session mode, the models used for chat, scheduled tasks and voice calls, and which slash commands are available. Only the fields you pass change. A running or starting agent restarts to apply the change. Calling it with only agent_guid refreshes the setup status of an agent waiting for setup, after its credentials were set. Skills, credentials and custom instructions have their own tools (apply_agent_skills, set_agent_credentials, manage_agent_custom_skill). On a team agent this needs a team admin or the person who deployed it; other team members can read the agent with get_my_agent and message it.

Input Schema

Name	Required	Description
`cover`	No	New https cover image URL; null goes back to the template cover.
`title`	No	New name.
`timezone`	No	IANA timezone such as "Europe/Istanbul" for scheduled tasks; null or "UTC" means UTC.
`agent_guid`	Yes	The deployed agent's guid, from list_my_agents or deploy_agent.
`categories`	No	New category list (at least one).
`chat_model`	No	Model for chat turns: a slug from the model list in get_my_agent, which shows each model's credits per 1M tokens. null resets to the default. The plan price stays the same.
`cron_model`	No	Model for scheduled tasks; same rules as chat_model.
`description`	No	New description; null clears it.
`enabled_commands`	No	Slash commands the agent offers; [] hides all of them. Commands today: agent_help, new_session, agent_status, agent_limits, last_scan, last_heartbeat, agent_restart, clear_all_sessions, clear_history.
`voice_prep_model`	No	Model that prepares voice calls; same rules as chat_model.
`team_session_mode`	No	private gives each person their own chat history; collaborative shares one history in team chats.
`voice_postcall_model`	No	Model that summarizes voice calls; same rules as chat_model.

Output Schema

Name	Required	Description	Default
`agent`	Yes
`changed`	Yes
`message`	Yes
`restarted`	Yes
`nextAction`	No

Schema Changelog

Changes observed during successful MCP inspections.

Addedv1.4.1Nov 1, 2026

TDQS

A4.8/5.0

Behavior5/5

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

Annotations only declare the safety profile (readOnlyHint=false, destructiveHint=false, idempotentHint=false); the description adds behavior they don't carry: partial-update semantics ('Only the fields you pass change'), the side effect that 'a running or starting agent restarts to apply the change', a setup-status refresh mode when called with only agent_guid, and the permission model for team agents. That is exactly the kind of impact disclosure an agent needs before invoking a mutation.

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

Conciseness4/5

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

The core purpose and the 'only fields you pass change' rule are front-loaded, and each following sentence carries distinct information (restart, refresh mode, sibling tools, permissions). It is dense and long for a single block, but essentially no sentence is filler.

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 12-parameter mutation tool, the description covers what changes, that unspecified fields are preserved, the restart side effect, the refresh-only calling mode, permission requirements, and where the excluded fields live. With an output schema available and 100% schema coverage, nothing material an agent needs before calling is missing.

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?

Schema coverage is 100% and already documents each field thoroughly, so the baseline is 3; the description adds value by declaring partial-update semantics and grouping the settings by purpose (timezone for scheduled tasks, models split across chat/cron/voice). It doesn't restate the per-parameter formats, but it doesn't need to.

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 and resource ('Change a deployed agent's name, description, cover or categories, and its settings') and then enumerates the settings that can be changed. An agent can distinguish this from deploy_agent, get_my_agent or control_agent without consulting 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?

Explicitly routes adjacent needs to the right siblings: 'Skills, credentials and custom instructions have their own tools (apply_agent_skills, set_agent_credentials, manage_agent_custom_skill)'. It also names the fallback path for users without permission ('other team members can read the agent with get_my_agent and message it'), so both when-to-use and when-not-to-use are covered.

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