Skip to main content
Glama

NEM Explorer (ScadaMiner)

report_gap

Idempotent

Tell the NEM Explorer team about something the user needed that these tools could not deliver. Optional and free: it costs no credits and does not change your answer. Call it ONLY when you were blocked, when a workaround failed, or when you had to give a narrower answer than the user asked for: the warehouse does not hold the data (missing_data), no tool or capability could do the job (missing_tool), the schema sent you down a wrong path (confusing_schema), or a tool returned something that looked wrong (wrong_result). Never call it on a question you answered in full, never as general feedback or praise, and at most once per gap per question. Pass the question_id from start_question, then wanted (what the user asked for that you could not deliver, with no names or other personal details) and tried (what you did instead). The user's answer comes first: report the gap alongside the answer, never instead of it.

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": {
      "category": "<category>",
      "wanted": "<wanted>",
      "tried": "<tried>"
    },
    "name": "report_gap"
  }
}

Input Schema

NameRequiredDescriptionDefault
triedYesWhat you did instead: the workaround, the narrower answer you gave, or where you stopped.
wantedYesWhat the user asked for that you could not deliver, in a sentence or two. Describe the need, not the person: no names, emails or organisations.
categoryYesWhat kind of gap. `missing_data`: the warehouse does not hold what the user asked about. `missing_tool`: the data is there but no tool or capability could do what they needed. `confusing_schema`: table or column names, descriptions or caveats sent you down a wrong path. `wrong_result`: a tool returned something that looked wrong. `other`: none of these.
question_idNoThe `question_id` from `start_question`. It ties the report to the trace of what you tried, which is most of its value. Omit it only if you never called `start_question`.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.6/5.0
Behavior4/5

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

The description adds real context beyond the annotations: it costs no credits, does not change the answer, must carry no personal details, and should accompany the answer rather than replace it. Indicator-based facts already covered by openWorldHint/idempotentHint/destructiveHint are not repeated verbatim, so the description's added value is meaningful, though it does not say who receives the report or what happens after submission.

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 in the first sentence and the exclusions follow in a logical order. It is dense and long for a single paragraph, and the category list duplicates the enum descriptions in the schema, but nearly every clause carries actionable constraint.

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 four-parameter write tool with no output schema, the definition covers triggers, non-triggers, frequency, parameter provenance, privacy limits, and ordering with respect to the user's answer. Nothing an agent needs in order to invoke it correctly is missing.

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 a cross-tool dependency the schema cannot: `question_id` must come from `start_question`, and it explains why (it ties the report to the trace), plus an explicit privacy constraint on `wanted`.

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 states a specific verb and resource: 'Tell the NEM Explorer team about something the user needed that these tools could not deliver.' No sibling tool does anything similar, so the agent can identify this as the sole gap-feedback channel.

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 explicit trigger conditions (blocked, workaround failed, or a narrower answer was required), explicit exclusions ('Never call it on a question you answered in full, never as general feedback or praise'), a frequency cap (at most once per gap per question), and a sequencing rule ('The user's answer comes first').

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.