Skip to main content
Glama
FLUF-io

@fluf/mcp

Official
by FLUF-io
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Remote

report_bug

File a bug report with FLUF support when a user reports an unresolvable FLUF issue, or when a FLUF tool fails or gives contradictory results.

Instructions

Raise a bug with FLUF support. Two situations call for it, and the second is the one that gets missed:

  1. The user describes a problem with FLUF that you can't resolve yourself.

  2. YOU hit the problem — a FLUF tool keeps failing, returns something that contradicts itself or the user's account, or leaves you unable to finish the task. The user never has to mention it first, and being stuck is not a reason to keep retrying quietly. File the report, then tell the user what you filed. KEEP IT SHORT. This arrives as a direct message in a human inbox: a title, two or three sentences, and the identifiers. Long reports get read last. Don't file for things the user can fix themselves (expired token, lapsed plan, a channel needing reauthorisation) — tell them the fix instead. Their account identity is attached automatically — don't ask for it. Replies arrive in the user's FLUF inbox.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
titleYesOne line naming the broken thing. No preamble, no severity word.
contextNoIdentifiers and raw error text only — FID/EID/VID, channel, listing id, the exact error string, a URL. One per line, no sentences. HARD LIMIT 500 characters.
severityNoHow blocking is this for the user. Default: medium.
descriptionYesWhat broke and what you expected instead. HARD LIMIT 500 characters — aim for two or three sentences. This is a support DM a person reads, not an incident report: no background, no restating the conversation, no rationale for why it matters, no summary of what you already tried.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed3 schema fields changedv0.2.7
    • changedInput schema / properties / context / description
      Previous value: -"Optional extra context — URLs, channel, product ID (FID/EID/VID), error messages, screenshots referenced by URL."New value: +"Identifiers and raw error text only — FID/EID/VID, channel, listing id, the exact error string, a URL. One per line, no sentences. HARD LIMIT 500 characters."
    • changedInput schema / properties / description / description
      Previous value: -"What went wrong, what you expected, and steps to reproduce."New value: +"What broke and what you expected instead. HARD LIMIT 500 characters — aim for two or three sentences. This is a support DM a person reads, not an incident report: no background, no restating the conversation, no rationale for why it matters, no summary of what you already tried."
    • changedInput schema / properties / title / description
      Previous value: -"Short bug title"New value: +"One line naming the broken thing. No preamble, no severity word."
  2. First observedv0.1.0

TDQS

A4.8/5.0
Behavior5/5

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

With no annotations, the description carries the full burden and does so: it discloses the delivery destination (a human inbox as a direct message), the reply channel (the user's FLUF inbox), that account identity is auto-attached, and that retrying quietly instead of filing is wrong. These are non-obvious operational facts an agent could not infer from the 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 conditions, then constraints; every sentence contributes something (trigger conditions, exclusions, length, identity handling, reply path). It runs somewhat long for a four-parameter tool, but the density is justified rather than padded.

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?

No output schema and no annotations, yet the description covers what the agent needs: when to file, when not to, how long the report should be, what the fields should contain in spirit, that identity is auto-attached, and where the reply lands. Nothing material 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. The description adds real meaning beyond the schema: the 'keep it short' constraint, the rationale (long reports get read last), and the explicit prohibition on asking for identity or including background/retried steps. It stops short of documenting each field individually, which the schema already handles.

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?

Opens with a specific verb and resource: 'Raise a bug with FLUF support.' The two enumerated triggering situations make the scope unambiguous, and no sibling tool (list_products, crosslist, approve_draft, etc.) overlaps with this function.

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?

Explicitly names both when-to-use conditions, including the counterintuitive one (agent hit the problem itself), and adds a clear when-NOT-to-use exclusion list (expired token, lapsed plan, channel reauthorisation) with the alternative action ('tell them the fix instead').

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

Deploy Server

Other Tools