Skip to main content
Glama
Sign In

Tulina

by ai.tulina.mcp
OverviewDiscussionsAdmin

run_finish

Close a run opened with run_start, with one outcome:

  • done — everything asked is done.

  • partial — the run ended cleanly but did only part of the work: note is REQUIRED and says what is done and what remains.

  • blocked — stopped by an obstacle it cannot lift alone (access, missing data, a cap, a human decision).

  • failed — an error broke the run.

Whatever the outcome, the rows the run still held go back to the queue (rows_released).

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": {
      "run_id": "<run_id>",
      "outcome": "<outcome>"
    },
    "name": "run_finish"
  }
}

Input Schema

NameRequiredDescriptionDefault
_orgNoOrg (id) de CET APPEL. `oto_list_orgs()`.
noteNowhat worked, where it broke, what was missing — required for partial.
_groupNoÉquipe (id) de CET APPEL, sous son org parente.
run_idYesthe id returned by run_start.
outcomeYesone of done | partial | failed | blocked.
_projectNoProjet (id) de CET APPEL — jeton PRIMAIRE. `oto_project(op='list')`.

Schema Changelog

Changes observed during successful MCP inspections.

No schema history has been recorded yet.

TDQS

A4.4/5.0
Behavior4/5

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

With no annotations, the description carries the load and does disclose the key side effect: whatever rows the run still held are released back to the queue (`rows_released`). It also flags that `note` is REQUIRED for partial. It does not cover permissions, idempotency, or what happens if the run_id is unknown or already closed.

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-loaded one-line purpose followed by a tight bulleted enumeration of outcomes and a closing sentence on row release. No filler, and the structure matches how an agent will read it: pick an outcome, then supply the note.

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?

For a terminal mutation tool with no output schema, the description covers the outcome vocabulary, the conditional requirement, and the queue-release side effect — enough to invoke it correctly. Error cases (bad run_id, double-close) are the only notable gap.

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 100%, so baseline is 3, but the description adds real semantic content the schema lacks: it explains what each outcome value means operationally (done/partial/blocked/failed) rather than just listing the allowed strings. The `note` requirement is reinforced with guidance on what to write ('what is done and what remains').

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 a specific verb and resource ('Close a run opened with `run_start`') and immediately names the counterpart tool, so it is distinguishable from run_start and from the apify_* run tools. The required `outcome` argument is named in the first line.

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?

The pairing with run_start makes the calling context clear, and the per-outcome definitions effectively tell the agent which outcome to choose. It does not explicitly say when NOT to close a run (e.g. an abandoned run, or aborting versus finishing), so one point is withheld, but the selection guidance among outcomes is strong.

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

All Tulina toolsInspect
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