Skip to main content
Glama

NEM Explorer (ScadaMiner)

list_capabilities

Read-onlyIdempotent

List supported analytical capabilities. Each capability is a typed, deterministic product surface — given typed params it returns SQL, a chart spec, and (when applicable) a pre-rendered markdown answer. Identical to what the chat product runs internally, so capability output stays consistent across surfaces. Returns every capability's id and description. Pass the current user question (or a question_id from start_question) to get a matched_capability recommendation when the deterministic matcher identifies a fit: the exact capability_id, the params derived from the question, and that capability's params_contract (required fields, enums, defaults, aliases) and params_schema. Pass capability_id to get the same contract for any one capability.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "list_capabilities"
  }
}

Input Schema

NameRequiredDescriptionDefault
questionNoOptional user question to match against the registered capability catalogue. When supplied, the response includes `matched_capability`; when it names a capability, that carries the exact capability id, the params derived from the question, and its `params_contract` and `params_schema`.
question_idNoOptional UUID returned by an earlier `start_question` call. When provided and `question` is omitted, the server looks up the stored question and matches the capability catalogue against it.
capability_idNoOptional exact capability id from the catalogue. When set, the response is that one capability's `params_contract` and `params_schema` instead of the catalogue; no question matching is done.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A3.9/5.0
Behavior4/5

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

Annotations already cover read-only, idempotent, non-destructive and open-world. The description goes beyond them by disclosing the return shape in each mode (all ids+descriptions, or matched_capability with derived params, params_contract and params_schema) and by asserting determinism and cross-surface consistency with the chat product. The matching is only described as "deterministic matcher identifies a fit" without saying what happens on a miss, which keeps it below 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?

Purpose is front-loaded and each mode is introduced in order, but the sentence "Identical to what the chat product runs internally, so capability output stays consistent across surfaces" is justification rather than actionable instruction and could be trimmed. The rest is dense with useful content.

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?

With no output schema, the description carries the burden of explaining returns, and it does so for all three modes including nested `params_contract` and `params_schema`. Residual gaps (what an unmatched question returns, ordering of the catalogue) are minor for a discovery tool whose safety profile is already in annotations.

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 documents all three optional params, including the question/question_id precedence and capability_id short-circuit. The description restates the same semantics with a little extra framing (matcher behavior, derived params), so the baseline 3 applies.

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 leads with a specific verb+resource ("List supported analytical capabilities") and defines what a capability is: a typed, deterministic surface returning SQL, a chart spec, and optionally markdown. It doesn't name the executor sibling (run_capability), so the agent must infer that this tool discovers and that one runs, but the discovery role is unambiguous.

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 clearly states three usage modes and the condition that selects each: bare call for the catalogue, `question`/`question_id` for a `matched_capability` recommendation, `capability_id` for a single contract. It gives no explicit exclusions or a named alternative, so an agent could still wonder when to skip this and call run_capability directly.

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.