Skip to main content
Glama
wiroai

Wiro MCP Server

Official
by wiroai

Change an agent's skills

apply_agent_skills
Idempotent

Turn registry skills on or off for a deployed agent and optionally upgrade Starter to Pro as one billed change: get a price quote, then confirm with its idempotency key.

Instructions

Turn registry skills on or off for a deployed agent, and optionally move it from Starter to Pro, as one billed change. Skills set the agent's monthly price and monthly credits. On a team agent only a team admin or the person who deployed the agent can change its skills; other members are refused and nothing is charged. Steps: 1) call without confirm. The tool checks the names, adds the skills they depend on, and returns the current and new monthly price, an estimate of what is charged now and an idempotency_key. Nothing changes yet. 2) Show the price to the user. 3) After they approve, call again with confirm: true and that idempotency_key. The key is tied to the quoted prices: if the price changed since the quote, nothing is applied and a new quote with a new key comes back. Reusing the key after a timeout is safe, the change is applied once. Billing: on a prepaid plan the monthly difference for the days left in the period is taken from the wallet at once, or credited to it when the price drops, and that credit can be spent until the period ends; on a card plan it is added to the next invoice. A running agent restarts once to load the skills. Newly enabled skills may still need credentials (set_agent_credentials, connect_agent_oauth) and do not create scheduled tasks (manage_agent_custom_skill does). Find skill names with list_agent_skills and the agent's current skills with get_my_agent. The agents playbook (get_playbook) has the full setup walkthrough.

Input Schema

NameRequiredDescriptionDefault
tierNoOptional: also move from Starter to Pro in this billed change. To upgrade without a skill change, use manage_agent_billing (upgrade_to_pro).
skillsYesSkills to change, as name: true to turn on or name: false to turn off, for example {"int-instagram-post": true}. Registry names only (list_agent_skills). Custom skills and scheduled tasks (cs-...) are managed with manage_agent_custom_skill; channels such as Telegram turn on through set_agent_credentials.
confirmNofalse (default) only returns the quote. true applies the change and charges it; it needs the idempotency_key from the quote.
agent_guidYesThe deployed agent's guid, from list_my_agents.
idempotency_keyNoWith confirm: true, the key from the quote the user approved. It ties the approval to the quoted prices, and repeating the call with it after a timeout never applies the change twice. Omit it to get a quote.
add_dependenciesNoAlso turn on the skills that the enabled skills depend on (default true). Without them the change is refused.

Output Schema

NameRequiredDescriptionDefault
tierYes
errorNo
statusYes
billingYes
changesYes
pricingNo
restartYes
agentGuidYes
nextActionNo
agentStatusYes
priceChangedNo
enabledSkillsNo
idempotencyKeyNo
credentialsNeededYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. Addedv1.4.1

TDQS

A4.9/5.0
Behavior5/5

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

Despite annotations already covering idempotency and read/write safety, the description adds substantial behavioral detail: no charge on refused admin/deployer attempts, quote-only first call, price-bound idempotency key, prepaid/card billing treatment, one restart, and credential/scheduling side effects. These are exactly the operational traits an agent needs before invoking a billed mutation.

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

Conciseness5/5

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

It is long but structured and front-loaded: purpose first, then permission constraints, quote/confirm steps, billing behavior, and related tools. Given the high-stakes two-step billed mutation, every section earns its place.

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?

Complete for a complex billed mutation: annotations, schema, and output schema already cover structured details, while the description explains permissions, idempotency flow, billing timing, restart behavior, and related tools. No critical invocation context 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%, so the schema already documents each parameter; the description still adds practical semantics around confirm/idempotency_key sequencing, registry-only skill names, add_dependencies refusal behavior, and when to use tier versus manage_agent_billing. The extra value is meaningful but partly overlaps schema descriptions.

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: turns registry skills on/off for a deployed agent, with optional Starter-to-Pro movement as one billed change. It clearly distinguishes this from custom skill, credential, and billing-only sibling tools.

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 guidance through a numbered quote-then-confirm workflow and names alternatives: manage_agent_billing for upgrade-only, manage_agent_custom_skill for custom/scheduled skills, and set_agent_credentials/connect_agent_oauth for credentials. It also covers permission restrictions and refusal behavior.

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