mcp-server

report_mcp_issue

Report a problem, gap, or workaround with THIS MCP toolset back to the Koongo team so it can be fixed or extended. Use this to report a tool error or a missing capability to Koongo. Use it when: a tool returned an error you could not resolve after a legitimate attempt (ESPECIALLY a 500 / unexpected server error or an unreachable-facade error), a capability you needed is missing, a tool's result was wrong or confusing versus what its docs implied, or you and the user AGREED on a manual workaround because MCP could not do something — or whenever the user says 'report this'. This is BACKGROUND product feedback, not a user-facing action and not something the user's task depends on: briefly ask the user's OK first ('want me to report this?'), file ONE report per scenario, then continue — do NOT loop or re-file the same thing. Provide category + a short title + a detailed description (what the user wanted, what actually happened, and any agreement/workaround). Strongly include steps[] — the CALL STACK: the sequence of tools you called with their key arguments and each one's outcome/error — plus the specific error, and expected vs actual where relevant, so an engineer can reproduce from the report alone. Never put credentials, tokens, API keys or personal data in a report (the server redacts known-sensitive keys defensively, but you must not include them). Returns {status:'recorded', reportId, ts}.

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>",
      "title": "<title>",
      "detail": "<detail>"
    },
    "name": "report_mcp_issue"
  }
}

Input Schema

Name	Required	Description
`error`	No	The specific error message/payload, if any.
`steps`	No	The call stack: the ordered tools you called with their key arguments and each one's outcome/error that led to this report.
`title`	Yes	A short one-line summary of the issue.
`actual`	No	What actually happened.
`detail`	Yes	Full description: what the user wanted, what actually happened, and any workaround/agreement made with the user.
`context`	No	Optional ids that help reproduce (project/marketplace/ad/feed/rule/attribute).
`category`	Yes	What kind of report: error \| missing_capability \| wrong_result \| confusing \| workaround \| suggestion.
`expected`	No	What you expected to happen.
`severity`	No	How badly it blocks the user: low \| medium \| high.

Schema Changelog

Changes observed during successful MCP inspections.

First observedSep 1, 2026

TDQS

A4.8/5.0

Behavior5/5

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

Annotations only declare the write/non-idempotent/non-destructive profile; the description adds what they cannot: this is background product feedback, the user's task does not depend on it, obtain user consent first, one report per scenario, no re-filing loops, and an explicit privacy rule against credentials/personal data with server-side redaction as a defensive backstop. It even states the return shape ({status, reportId, ts}) despite having no output schema.

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?

Front-loaded with purpose then a 'Use it when:' trigger list, followed by operational constraints and content guidance; nearly every sentence carries a distinct instruction. It runs long and packs several ideas into single sentences with parentheticals and emphasis, which slightly reduces scanability.

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 9-parameter nested-object tool with no output schema, the description covers triggers, consent and dedupe behavior, privacy constraints, required report content, nested steps[] guidance, and the return payload. Nothing an agent needs in order to file a correct, reproducible report 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 per-field descriptions already define each parameter. The description goes beyond baseline by prescribing the content contract: category + short title + detailed description covering user intent, actual outcome and workaround, plus a strong instruction to populate steps[] as an ordered call stack with arguments and per-step outcomes so an engineer can reproduce from the report alone.

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?

"Report a problem, gap, or workaround with THIS MCP toolset back to the Koongo team so it can be fixed or extended" gives a specific verb, resource, and recipient. No sibling tool does anything similar, so it is instantly distinguishable from the marketplace/feed/rule CRUD tools.

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?

Explicit trigger list: unresolved tool errors (especially 500s or unreachable-facade errors), missing capabilities, wrong/confusing results versus docs, agreed manual workarounds, or the user saying 'report this'. It also states when-not framing (not user-facing, not task-blocking) and the alternative behavior (ask the user's OK, file one report, then continue rather than looping).

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

All mcp-server tools Inspect

Try in Browser

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources

Need Help?