FlowState Hosted

manage_todos

Destructive

Todos. list; next: top unblocked (others' claims last). update: status, priority or title, when done and before you end. block / unblock: waits on todos or a problem. add: subtask, blocker or due date only (else log_work). claim before you start (fails if someone has it); renew; release or handoff (with a note). Returns 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>",
      "project": "<project>"
    },
    "name": "manage_todos"
  }
}

Input Schema

Name	Required	Description
`sort`	No	list: default priority.
`limit`	No	next: how many (default 5).
`model`	No	Model name if known. Never guess.
`title`	No	add (required) / update.
`action`	Yes	The operation; see the tool description.
`status`	No	update: new. list: filter.
`compact`	No	list: shorter rows.
`minutes`	No	claim / renew: 1-120, default 15.
`project`	Yes	Project name or id. Required.
`todo_id`	No	#id in the brief.
`due_date`	No	add: ISO due date.
`priority`	No	add / update. list: filter.
`next_step`	No	handoff: the next step.
`blocked_by`	No	Todo ids it waits on.
`description`	No	add / update.
`where_i_was`	No	handoff: your progress.
`component_id`	No	add: component id.
`min_priority`	No	list: this or more urgent.
`parent_todo_id`	No	add: parent todo id.
`blocked_by_problem`	No	Problem id it waits on.

Schema Changelog

Changes observed during successful MCP inspections.

First observedNov 7, 2026

TDQS

A3.6/5.0

Behavior3/5

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

Annotations declare destructiveHint=true, readOnlyHint=false, and idempotentHint=false, so the safety profile is already provided. The description adds operational behavior such as claim failure on conflict, ordering of others' claims in next, handoff note requirements, and 'Returns rows', but it does not explain what destructive mutations affect or whether changes are reversible.

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 description is dense but front-loaded and organized by action, with no filler. Some clauses are telegraphic, such as 'when done and before you end', but the brevity is appropriate for a 20-parameter multi-action tool.

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 10-action, 20-parameter mutation tool with no output schema, the description covers action purposes and key caveats but omits detailed side effects and comprehensive action-to-parameter mapping. The 100% schema coverage compensates substantially, but 'Returns rows' is thin and destructive behavior remains underspecified.

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 already maps parameters to actions, such as limit for next, minutes for claim/renew, and blocked_by for block. The description adds broad action-to-parameter hints like update status/priority/title and add subtask/blocker/due date, but does not add syntax or constraints beyond the schema.

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 names the resource (Todos) and enumerates ten actions with a short purpose for each: list, next, update, block/unblock, add, claim, renew, release, and handoff. It distinguishes add from sibling log_work with 'else log_work', though it does not fully differentiate from other manage_* siblings.

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 concrete when-to-use guidance for several actions: next returns top unblocked items with others' claims last, update is for status/priority/title when done and before ending, add is only for subtask/blocker/due date otherwise use log_work, and claim must happen before starting and fails if someone else has it. Guidance is missing for some choices such as list vs next and when to prefer block/unblock alternatives.

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?