Skip to main content
Glama

set_session_flow

Assigns a named flow to the current Claude Code session so Tares can record challenge exchanges and session summaries; pass an empty string to clear it.

Instructions

Mark this Claude Code session as running a named flow, e.g. "challenger" (a second model challenges your plan and every commit; Tares keeps the whole exchange and writes the session summary). Pass an empty string to clear it. Call it when the user asks for the flow at the start of a session. This tool only acknowledges: the Tares plugin sees the call in the transcript and marks the session on both the laptop and Tares.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "set_session_flow"
  }
}

Input Schema

NameRequiredDescriptionDefault
flowNochallenger

Output Schema

NameRequiredDescriptionDefault
resultYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv1.57.0

TDQS

A4.3/5.0
Behavior4/5

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

With no annotations, the description carries the full burden and does well: it discloses that the tool 'only acknowledges' and that a plugin observes the call in the transcript to mark the session on both the laptop and Tares. That non-obvious indirect side effect is exactly the kind of context annotations could not provide; it is slightly short on failure behavior for unrecognized flow names.

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?

Purpose is front-loaded in the first clause, followed by example, reset instruction, trigger, and mechanism in a logical order. The parenthetical explaining what 'challenger' does is useful but slightly long relative to the tool's simplicity.

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 needn't be described, and the description covers trigger, clearing behavior, and the plugin-mediated marking path. The main remaining gap is the set of valid flow names, which the schema (no enum) also leaves undefined.

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 0% and the single 'flow' parameter has no schema description, but the description compensates by explaining the value is a flow name, giving 'challenger' as an example, and specifying that an empty string clears the setting — semantics absent from the schema. It leaves open which other flow names are valid and what the 'challenger' default in the schema implies.

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?

The description states a specific verb and resource ('mark this Claude Code session as running a named flow') and grounds it with a concrete example value ('challenger') plus its meaning. An agent can distinguish this from sibling setters like set_crew_settings or set_stage without opening the 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?

It gives an explicit trigger ('call it when the user asks for the flow at the start of a session') and an explicit reset path ('pass an empty string to clear it'). It does not name alternatives or state when not to call it, but no clear sibling overlaps this session-scoped action.

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