FlowState Hosted

log_work

Record one decision (a choice and why), change, problem, learning or todo. Call it right after each decision, change, fix or lesson, and before you end or hand back. To update todos or problems: manage_todos / manage_problems. Only adds. Review mode or suggested=true may queue it. A shared-component change alerts linked projects. A close decision gets a possible-conflict note; act on it. conflicts_with opens a disagreement card. Secrets are refused. Returns {logged, record, note} or {queued_for_review}.

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": {
      "project": "<project>",
      "kind": "<kind>",
      "summary": "<summary>"
    },
    "name": "log_work"
  }
}

Input Schema

Name	Required	Description
`kind`	Yes	The record kind (see the description).
`model`	No	Model name if known. Never guess.
`topic`	No	Short topic, e.g. API sessions.
`source`	No	user_stated, ai_inferred or from_code.
`details`	No	Why, or old and new values. Max 10,000 chars.
`project`	Yes	Project name or id. Required.
`summary`	Yes	The record in one short line.
`category`	No	learning only: the kind of lesson.
`evidence`	No	Up to 2: file:line, or output:/url:/tool: text.
`priority`	No	todo or problem. Default normal.
`replaces`	No	Decision id this one replaces.
`component`	No	Component name; created if missing. Shared ones too.
`suggested`	No	true = queue it for the user's review.
`conflicts_with`	No	Record id this disagrees with.
`conflicts_with_type`	No	Default decision.

Schema Changelog

Changes observed during successful MCP inspections.

First observedNov 7, 2026

TDQS

A4.4/5.0

Behavior4/5

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

Beyond the annotations (which only declare non-readonly, non-destructive, non-idempotent, closed-world), the description discloses append-only behavior ('Only adds'), review-mode queuing, cross-project alerting on shared components, conflict-note generation, disagreement cards, and secret refusal. That is substantial behavioral context. It stops short of explaining what happens on a rejected secret or how the conflict note is surfaced, keeping it below a 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?

The core action and timing are front-loaded in the first two sentences, and the return shape is stated compactly at the end. It is dense and telegraphic in places ('A close decision gets a possible-conflict note; act on it'), but nearly every clause carries distinct operational information.

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

Completeness5/5

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

For a 15-parameter mutation tool with no output schema, the description covers the essential gaps: append-only semantics, queuing behavior, side effects on linked projects, conflict handling, secret rejection, and the return payload shape ({logged, record, note} or {queued_for_review}). An agent has enough to call it correctly and interpret the result.

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%, so the baseline is 3. The description does add meaning for a few parameters — 'suggested=true may queue it', 'conflicts_with opens a disagreement card', and shared 'component' triggering linked-project alerts — but the remaining twelve parameters (evidence, replaces, category, priority, source, model, topic) get no elaboration beyond the schema.

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 first sentence gives a specific verb (record) and enumerates the exact resource kinds (decision, change, problem, learning, todo), with a parenthetical defining what a decision record contains. It also names the sibling tools (manage_todos / manage_problems) that own the update path, so an agent can separate this from adjacent tools without opening a 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?

Explicit timing guidance is given: 'Call it right after each decision, change, fix or lesson, and before you end or hand back.' It also routes the agent away from this tool for updates ('To update todos or problems: manage_todos / manage_problems'), which is a clear when-not-to-use statement.

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?