FlowState Hosted

manage_sessions

Destructive

Inspect FlowState's sessions. They open and close by themselves (closed after 2 hours idle or when the app quits, with a summary queued for review), so this is rarely needed. current, list, conversations: read. start: returns the automatic session. end: close one with a summary (not undoable). Decisions go in log_work. Returns session or conversation rows.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "action": "<action>"
    },
    "name": "manage_sessions"
  }
}

Input Schema

Name	Required	Description
`limit`	No	list / conversations: max rows. Default 20.
`model`	No	Model name if known. Never guess.
`action`	Yes	The operation; see the tool description.
`project`	No	Project name or id. Required except for current.
`summary`	No	end: what was accomplished.
`outcomes`	No	end: short outcome lines.
`session_id`	No	end: the session's id (required). conversations: only this session.
`focus_problem_id`	No	start: problem in focus (ignored if a session is open).
`focus_component_id`	No	start: component in focus (ignored if a session is open).

Schema Changelog

Changes observed during successful MCP inspections.

First observedNov 7, 2026

TDQS

A4.6/5.0

Behavior5/5

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

Annotations already flag destructiveHint=true, and the description earns credit by explaining what that means concretely: end requires a summary and is "not undoable", while auto-closed sessions queue a summary for review. It also discloses that focus ids are ignored when a session is already open, a behavioral detail available nowhere in 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.

Conciseness5/5

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

Front-loads the rarely-needed warning, then packs action semantics into terse clauses with zero filler. Every clause either routes the agent or discloses behavior; nothing is redundant.

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?

Covers all five actions, the destructive end path, and the return shape ("session or conversation rows") for a 9-parameter multi-action tool with no output schema. Minor gap: it doesn't say what current returns when no session exists or what the default listing covers, though that is inferable from the schema.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100% and each parameter is already annotated per action (limit, session_id, summary, focus ids), so the description adds little parameter-level meaning beyond restating the read/write split. Baseline 3 applies when the schema carries the load.

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 the resource (FlowState sessions) and enumerates every action with its semantics: current/list/conversations are reads, start returns the automatic session, end closes one with a summary. It also names the sibling boundary explicitly ("Decisions go in log_work"), so an agent can separate session lifecycle from work logging without opening either 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?

Gives a direct when-not-to-use signal ("They open and close by themselves... so this is rarely needed") and explains the lifecycle that makes it unnecessary. It also routes the adjacent use case to log_work, so the agent knows which tool handles decisions instead of misusing end/start.

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

All FlowState Hosted tools Inspect

Try in Browser

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources

Need Help?