Agents-Core

Overview Schema Source Related Servers Discussions Admin

Choose a flow's persona

set_flow_persona

DestructiveIdempotent

Assign an agent, skills, implants and rules to a flow by replacing its frontmatter persona, or reset the choice so the flow's original configuration applies again.

Instructions

Choose the agent, skills, implants and rules a flow runs with, for this user.

Works for built-in, user: and repo: flows without copying their text; it
replaces the persona in the flow's frontmatter. A list loads exactly those
components (empty = none); an omitted list keeps the agent's own selection.
agent omitted: run the flow without a persona. reset=true (alone): drop this
choice so the flow's frontmatter applies again; it also repairs a broken one.
IDs: agent names as in list_agents; skills and implants by file ID
(skill-web-search, implant-iteration-budget, not footer short names);
rules by name (no-fabrication).

Input Schema

TableJSON Schema

Name	Required	Description
`flow`	Yes
`agent`	No	Agent name for the flow persona.
`reset`	No
`rules`	No	Optional rule names, as a JSON array of strings.
`skills`	No	Optional skill ids, as a JSON array of strings.
`implants`	No	Optional implant ids, as a JSON array of strings.
`workspace`	No	Absolute path of your working directory, the project this session works in. Pass it whenever you have one: one server can serve several sessions.

Output Schema

TableJSON Schema

Name	Required	Description	Default
`result`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

First observedv26.10.14+1807Oct 15, 2026

TDQS

A4.4/5.0

Behavior4/5

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

Annotations already declare destructiveHint=true, idempotentHint=true and openWorldHint=true, so the safety profile is covered. The description adds real context beyond that: it replaces the persona in the flow's frontmatter, does not copy flow text, and reset also repairs a broken frontmatter. Permission/auth requirements and error behavior are still unstated, keeping it short of 5.

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?

Front-loaded with the core action in the first clause, then layered with conditions; the ID-format line is dense but earns its place. Slightly long and clause-heavy, which costs it the top mark, but nothing is filler.

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

Completeness4/5

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

An output schema exists, so return values need no explanation, and annotations cover the mutation safety profile. For a 7-parameter mutation the description is nearly complete; only auth/permission expectations and failure modes remain unaddressed.

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 coverage is 71% and schema descriptions are thin ('Optional skill ids...'), yet the description distinguishes omitted vs empty lists, explains reset-only semantics, and disambiguates the ID formats (agent names per list_agents, skills/implants by file ID not footer names, rules by name). This adds substantial meaning the schema does not carry.

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 (choose/set) plus the precise resource (a flow's persona) and enumerates exactly what the persona consists of: agent, skills, implants, rules. It even scopes it ('for this user'), so an agent can distinguish it from sibling mutations like save_flow or delete_flow without opening any schema.

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

Usage Guidelines4/5

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

Gives rich conditional usage: works for built-in, user: and repo: flows; omitted list keeps the agent's own selection; omitted agent runs without a persona; reset alone drops the choice. What's missing is explicit routing to alternatives (e.g., when to prefer save_flow vs set_flow_persona), but the conditions are clear.

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

Deploy Server