Skip to main content
Glama
Sign In

Tulina

by ai.tulina.mcp
OverviewDiscussionsAdmin

run_start

Open a run (a tracked walkthrough) so a procedure can be reviewed later. Returns a run_id — keep it and pass it to run_finish when you're done. Every tool call until then is automatically attributed to this run.

Use it for a repeatable guide/skill (pass guide) AND for any one-shot procedure worth logging (omit guide).

Returns guide_version — the version of that procedure frozen for this run (null for an ad-hoc run, or if the slug matches no procedure you can read). The response also carries the deprecated doctrine/doctrine_version keys until 29/10/2026.

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": {
      "label": "<label>"
    },
    "name": "run_start"
  }
}

Input Schema

NameRequiredDescriptionDefault
_orgNoOrg (id) de CET APPEL. `oto_list_orgs()`.
guideNooptional — the guide/skill slug being executed (as passed to oto_procedure op=get). Omit for a one-shot/ad-hoc run.
labelYesshort human description of what this run does (always logged).
_groupNoÉquipe (id) de CET APPEL, sous son org parente.
_projectNoProjet (id) de CET APPEL — jeton PRIMAIRE. `oto_project(op='list')`.
doctrineNoDEPRECATED alias of `guide`, removed on 30/11/2026 — pass `guide` instead.

Schema Changelog

Changes observed during successful MCP inspections.

No schema history has been recorded yet.

TDQS

A4.5/5.0
Behavior4/5

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

With no annotations, the description carries the full load and does disclose the key non-obvious side effect: all subsequent tool calls are attributed to the run, which is global state the agent must understand. It also discloses return keys and a deprecation window. It does not mention permissions or whether an open run can be abandoned/cleaned up, leaving those gaps.

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?

Front-loaded with the purpose, then the run_id contract, then the when-to-use split — a sensible order. The trailing paragraph about deprecated `doctrine` keys until 29/10/2026 is somewhat low-value trivia but does prevent confusion when the agent sees those keys, so it earns its place marginally.

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?

There is no output schema, so describing `run_id`, `guide_version`, and the deprecated `doctrine` keys is necessary and done well. For a session-opening mutation tool it is nearly complete, missing only permission/context requirements (how `_org`, `_group`, `_project` scope the run).

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 description coverage is 100%, so the baseline is 3, but the description adds decision-level meaning beyond the schema: when to supply `guide` versus omit it, and that `guide_version` is frozen for the run and null when the slug matches no readable procedure. It does not explain the `_org`/`_group`/`_project` context parameters at all, leaving the schema to carry them.

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 ('Open a run') and immediately defines the unfamiliar term ('a tracked walkthrough') so the agent knows what a run is. It implicitly distinguishes itself from the sibling run_finish by naming it as the closer, and the pair forms an obvious bracket.

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 explicit selection rules: pass `guide` for a repeatable guide/skill, omit it for a one-shot procedure worth logging. It also names the paired tool (`run_finish`) and the lifecycle ('every tool call until then is automatically attributed'), so the agent knows both when to open a run and when to close it.

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