Skip to main content
Glama

NEM Explorer (ScadaMiner)

pin_live_query

Idempotent

Keep a live query URL alive, name it, or kill it (#2374). Every execute_sql over the curated warehouse returns a live_url — a link that re-runs THAT query and returns the latest rows as JSON on a plain GET, with no API key, because the id in the link is the access and it grants only that one query. Those links last 24 hours. Pin one the moment a user is going to put it anywhere durable: a dashboard they host, an HTML file, an embedded widget, a chart they want to keep. Omit days for an indefinite link — that is usually what they want. Pass revoke: true to kill a link permanently; re-creating the same query then gives a DIFFERENT url, so the old one stays dead. Whenever you hand a user a live URL, tell them plainly that anyone with the link can read that data.

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": {
      "live_url": "<live_url>"
    },
    "name": "pin_live_query"
  }
}

Input Schema

NameRequiredDescriptionDefault
daysNoHow many more days it should answer for. **Omit for indefinite** — the right choice when the user is putting the URL somewhere durable, which is the whole reason to pin one.
labelNoWhat this link is for, in the user's words: "SA wind vs price, hourly". Shown in `list_live_queries`, which is the only way anyone tells their links apart later.
revokeNoPass `true` to kill the URL instead. Immediate and permanent: anything polling it starts getting 404s, and pinning the same SQL again mints a NEW url, so whoever holds the old one stays locked out.
live_urlYesThe live query to keep, as the `live_url` an `execute_sql` response returned or the bare id out of it. Both work — pass whichever you have.
question_idNoOptional UUID returned by an earlier `start_question` call. When provided, this tool call is attributed to that question.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.7/5.0
Behavior5/5

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

Annotations only say readOnly=false, idempotent=true, destructive=false; the description adds the behavior that actually matters: links expire after 24 hours by default, the URL is unauthenticated because the id itself is the capability, revoke is immediate and permanent (pollers get 404s), and re-pinning after revoke mints a new URL rather than resurrecting the old one. It also discloses a security obligation (warn the user that anyone with the link can read the data), which no annotation conveys.

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?

It is front-loaded with the action and then a single dense paragraph that mostly earns its length, since the expiry window and the capability-URL security model are non-obvious. The one redundancy is the `revoke` sentence, which restates the schema's `revoke` description almost verbatim ('pinning the same SQL again mints a NEW url').

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, and the description never says what a successful pin returns — presumably the durable URL and its expiry — which is the one thing an agent needs to relay to the user. Everything else a caller needs (when to pin, default duration, permanent revocation semantics, the confidentiality warning) is present and precise.

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 the baseline is 3, but the description adds advisory meaning beyond the field docs: it states that omitting `days` is the recommended default for the main use case, and it frames `revoke` in terms of the observable consequence for anyone polling the URL. It does not add anything new about `label` or `question_id`, which is the only reason this is not a 5.

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 names a concrete verb set (keep alive / name / kill) against a concrete resource (a live query URL), and the rest of the description explains exactly what that object is — a re-runnable link minted by `execute_sql`. It is clearly distinguishable from siblings like `execute_sql` (which creates the link) and `list_live_queries` (which enumerates pinned ones).

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?

It gives an explicit trigger ('the moment a user is going to put it anywhere durable: a dashboard they host, an HTML file, an embedded widget, a chart'), an explicit default choice ('Omit `days` for an indefinite link — that is usually what they want'), and a separate condition for the destructive branch (`revoke: true`). It also names the sibling tools in the workflow (`execute_sql` produces the URL, `list_live_queries` shows labels), so the agent knows where this sits in the sequence.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.