Skip to main content
Glama

AINDEX

Tell AINDEX what went wrong, or right

send_feedback

Send the AINDEX team a short report about AINDEX or this MCP server: an issue (the instructions name a tool that does not exist, a quote failed for a token, a figure looks wrong), an idea, or praise. Before sending: remove anything personal (names, emails, wallet balances tied to a person, anything your human would not post publicly), never include a key or recovery phrase, and show your human the exact draft once and send it only if they agree. Token addresses are fine; shorten transaction hashes to their first 10 characters. One report per client every 5 minutes, so put everything in one. Reports are read by the AINDEX team and never shown to other users; nothing comes back but a reference.

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": {
      "kind": "<kind>",
      "summary": "<summary>"
    },
    "name": "send_feedback"
  }
}

Input Schema

NameRequiredDescriptionDefault
kindYesissue: something is wrong or failed. idea: something that should exist. praise: something that worked well.
toolNoThe tool concerned, if any, for example get_token_market.
detailsNoWhat you did, what you expected, what happened instead, and any error text. No personal data.
summaryYesOne line: what happened.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.6/5.0
Behavior5/5

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

Well beyond the annotations, it discloses the rate limit (one per client per 5 minutes), the audience (read by the AINDEX team, never shown to other users), and the return behavior (nothing comes back but a reference). It also states preconditions: redact personal data, never include keys or recovery phrases, and get human approval on the exact draft before sending.

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 a single dense paragraph with the purpose front-loaded and no filler sentences; each clause carries a distinct constraint. The privacy/redaction run is somewhat comma-heavy and could be broken into bullets for faster scanning, but nothing is redundant.

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 mutation with no output schema, it covers everything an agent needs: what qualifies, what must be redacted, the approval step, the rate limit, the audience, and what the call returns. No output schema is needed because the return is stated as just a reference.

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 real content guidance for the fields: token addresses are acceptable while transaction hashes should be shortened to their first 10 characters, and personal or wallet-tied data must be stripped. That meaningfully supplements the schema's maxLength and enum notes.

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 description opens with a specific verb and resource: send a report to the AINDEX team about AINDEX or this MCP server, and enumerates the three reportable categories (issue, idea, praise). That distinguishes it from informational siblings like about_aindex, which read rather than report.

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 gives a concrete batching rule ('One report per client every 5 minutes, so put everything in one') and spells out what qualifies as an issue (missing tool, failed quote, wrong figure). It does not explicitly route the agent elsewhere for reading information, but the when-to-use condition is clear.

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