Skip to main content
Glama

POPA Recon

Research a public question

research

Researches a factual question about a public web3 project, protocol, token, wallet, transaction or market event, in the language of the question. Starts a saved POPA Recon research request and returns the finished answer with cited sources, or a pending receipt; the research card follows a pending request live and shows the finished answer, and the answer tool reads the receipt when no card is shown. It covers research only: it gives no buy or sell advice or price predictions and makes no trades or transfers.

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": {
      "question": "<question>"
    },
    "name": "research"
  }
}

Input Schema

NameRequiredDescriptionDefault
questionYesThe question to research, in the user's language. It is researched on its own, without the chat history, so it states the project, token, address or event that any «it», «they» or «that one» refers to.

Output Schema

NameRequiredDescriptionDefault
stepsYes
answerYes
statusYes
balanceNo
buy_urlNo
sourcesYes
request_idYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.2/5.0
Behavior4/5

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

Adds meaningful behavior beyond the annotations: the call starts a saved research request (consistent with readOnlyHint=false), and the return may be either a finished cited answer or a pending receipt, with a research card tracking it live. That async/stateful disclosure is valuable. It stops short of saying how long a request typically takes, whether it can be polled or re-run, or what happens to duplicate requests, for which idempotentHint=false is the only signal.

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 and scope are front-loaded in the first clause, with the receipt/card mechanics and exclusions following. The middle sentence is long and mixes return-value behavior, UI card behavior, and sibling routing, and 'in the language of the question' is duplicated against the schema, but nothing is truly wasted.

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?

An output schema exists, so the description needn't enumerate return fields, and the annotations cover the open-world and non-destructive profile. Given one simple parameter, the description supplies everything else an agent needs: scope boundaries, async receipt semantics, language handling, and sibling routing.

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?

Only one parameter, and the schema description already covers it at 100% coverage, including the requirement to restate any referent without chat history. The description's phrase 'in the language of the question' largely restates the schema and adds no new syntax, format, or constraint information. Baseline 3 is appropriate.

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 (researches) plus a precisely bounded resource class: factual questions about public web3 projects, protocols, tokens, wallets, transactions or market events. It also draws the boundary against non-research asks and points at sibling behavior ('the answer tool reads the receipt'), so an agent can distinguish it from 'answer' without opening either schema.

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?

Gives clear when-to-use context (factual public web3 questions, asked in the user's language) and explicit exclusions (no buy/sell advice, no price predictions, no trades or transfers). It also explains the handoff to the 'answer' tool for reading a receipt when no research card is present, though it does not state what to do for private/non-public questions or what to use if the topic falls outside web3.

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.

Resources