FlowState Hosted

manage_problems

Destructive

Work on a project's existing problems (bugs, blockers). list: open problems. tree: one problem with every attempt and its solution. add_attempt: record a try. end_attempt: how a try ended. solve: close it with what fixed it (manage_history undo reopens it). Call add_attempt or solve right after a fix, and again before you end or hand back. Open a new problem with log_work kind=problem. Reads: list, tree. Writes need project. Returns problem rows, the tree, or the saved attempt or solution.

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_problems"
  }
}

Input Schema

Name	Required	Description
`model`	No	Model name if known. Never guess.
`notes`	No	end_attempt: what you learned.
`action`	Yes	The operation; see the tool description.
`compact`	No	list: shorter rows.
`outcome`	No	end_attempt: how it ended (required).
`project`	No	Project name or id. Required for writes; list: omit for all projects.
`summary`	No	solve: what fixed it (required).
`attempt_id`	No	end_attempt: the attempt's id (from add_attempt or tree).
`confidence`	No	end_attempt: how sure. Default attempted.
`problem_id`	No	tree / add_attempt / solve: the problem's id.
`description`	No	add_attempt: what you tried (required).
`key_insight`	No	solve: the lesson, one sentence.
`code_snippet`	No	solve: the fix as text. No secrets.
`component_id`	No	list: only this component's problems.
`parent_attempt_id`	No	add_attempt: an earlier attempt this one builds on.
`winning_attempt_id`	No	solve: the attempt that worked.

Schema Changelog

Changes observed during successful MCP inspections.

First observedNov 7, 2026

TDQS

A3.8/5.0

Behavior4/5

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

Annotations declare destructiveHint=true, so the added note '(manage_history undo reopens it)' is genuinely useful recoverability context the agent would not otherwise have. It also discloses prerequisites ('Writes need project'), the return shapes, and a safety constraint ('No secrets' on code_snippet). It does not describe failure modes or what happens to attempts when a problem is solved.

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 action list is front-loaded and each fragment maps to one operation, with zero filler. The telegraphic phrasing ('end_attempt: how a try ended') trades some readability for density, and the final return-value sentence is slightly listy, but nothing is wasted.

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

Completeness3/5

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

For a 16-parameter, 5-action tool with no output schema, the description covers actions, workflow timing, prerequisites, and return values, which is close to sufficient. Gaps remain: which parameters are mandatory per action is only partly restated, and the ordering/relationship between add_attempt, end_attempt, and solve (an attempt must be ended before solving?) is left implicit.

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 the schema itself assigns most parameters to actions ('end_attempt: ...', 'solve: ...'), so the baseline is 3. The description does carry the per-action meaning of the `action` enum, which the schema explicitly defers to it for, but it adds little beyond the schema on the other 15 parameters.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description states the resource (a project's existing problems, bugs/blockers) and enumerates all five actions with a short gloss for each (list, tree, add_attempt, end_attempt, solve). It also routes creation elsewhere ('Open a new problem with log_work kind=problem'), so an agent can separate reads from this tool's write actions. The opening verb 'Work on' is vague and the per-action glosses are telegraphic ('end_attempt: how a try ended'), which keeps it short of a 5.

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 explicit timing guidance ('Call add_attempt or solve right after a fix, and again before you end or hand back') and names the alternative for a adjacent need ('Open a new problem with log_work kind=problem'). It also flags the read/write split and that writes require a project. There is no explicit when-not-to-use guidance beyond that.

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?