Skip to main content
Glama

Feedback: Report bug

feedback_report_bug
Destructive

Report a bug to the Nilyo team as a tracked issue. Use after a tool failed unexpectedly (TOOL_FAILED, wrong or empty result, broken flow) and the user agrees to report it; also when the user says 'ça ne marche pas' / 'report this'. Include the exact error code and details from the failing result so engineers can reproduce. Never include credentials, message bodies or third-party personal data. Ask the user for consent first (user_consent=true).

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": {
      "title": "<title>",
      "description": "<description>",
      "user_consent": "<user_consent>"
    },
    "name": "feedback_report_bug"
  }
}

Input Schema

NameRequiredDescriptionDefault
toolNoNilyo tool name involved, if any.
stepsNoMinimal steps to reproduce: which tools/arguments in which order (IDs can be included).
titleYesShort, specific title in English (what fails or what is wanted), e.g. 'email_list_messages fails on OVH IMAP mailbox with 501'.
actualNo
expectedNo
providerNoProvider involved when relevant: linkedin, whatsapp, instagram, telegram, gmail, outlook, imap, calendar.
severityNohigh = user blocked with no workaround; medium = wrong behaviour with a workaround; low = cosmetic.
error_codeNoError code returned by Nilyo, e.g. TOOL_FAILED, PROVIDER_VALIDATION_ERROR.
descriptionYesWhat the user was trying to do, in their words plus your observations. No passwords, tokens, message contents or third-party personal data.
user_consentYesMust be true: the user explicitly agreed to send this report to the Nilyo team.
error_detailsNoThe 'Details:' text of the failing result, verbatim.
sentry_event_idNoerror.sentry_event_id from the failing result, when present.
suspected_layerNoWhere you think the bug is: 'nilyo' (tool logic, resolution, errors, billing, connection flow) or 'unipile_api' (the provider connection layer returned an error like UNIPILE_5xx/provider/…). 'unknown' lets the server infer it.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.4/5.0
Behavior4/5

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

Adds real behavior beyond the annotations: a hard consent gate, a privacy prohibition on credentials, message bodies and third-party PII, and a requirement to include verbatim error code/details for reproducibility. It does not say what happens after submission (whether an issue ID is returned, or whether repeat reports are deduplicated), which matters since there is no output schema. The 'sends to the Nilyo team' framing is consistent with the annotations, not contradictory.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Purpose is front-loaded in the first clause, followed by trigger, content requirements, prohibitions and the consent precondition in a tight sequence with no filler. Every sentence carries an instruction the agent needs.

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?

For a 13-parameter mutation tool with no output schema, the description covers purpose, triggers, required evidence, privacy limits and consent. The remaining gap is the post-submission outcome (confirmation, issue identifier, failure modes if the team endpoint is down), which the agent cannot infer from structured fields.

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 already 85%, so most parameters are self-documenting, but the description still adds intent: error_code and error_details must be copied verbatim from the failing result, user_consent must reflect an explicit user agreement, and the report must exclude secrets and third-party data. That meaningfully constrains how several fields should be filled beyond their schema text.

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 bug to the Nilyo team as a tracked issue" gives a specific verb, recipient and artifact, and the word "bug" naturally separates it from the sibling feedback_request_feature. An agent can tell what this creates without opening the 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 explicit trigger conditions: a tool failed unexpectedly (TOOL_FAILED, wrong/empty result, broken flow) and the user agrees, plus the natural-language triggers 'ça ne marche pas' / 'report this'. It never names the sibling feedback_request_feature as the alternative for non-bug requests, so the boundary between the two feedback tools is left implicit.

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.