Skip to main content
Glama
Sign In

divux

by si.divux
OverviewDiscussionsAdmin

Report a problem or idea to Divux

send_feedback

Stores a short report for Divux: a wrong dated figure, a tool that failed, a tool that is missing, or an idea. Fields are kind, a summary of up to 300 characters, an optional tool name, and optional details of up to 1,000 characters. The text is stored as sent, so the fields are for general descriptions without personal details. Divux keeps the text and does not reply. The limit is 5 reports a day per connection. Applies to questions about reporting a problem with Divux or suggesting an idea to Divux.

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
kindYesType of report: a wrong dated figure, a broken tool, a missing tool or an idea.
toolNoName of the Divux tool involved, when one was involved.
detailsNoA short general description of the problem, without personal details.
summaryYesThe problem or idea in one or two general sentences, without personal details.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed3 schema fields changed
    • changedInput schema / properties / details / description
      Previous value: -"What was asked, what came back, and what the official source says, in general words."New value: +"A short general description of the problem, without personal details."
    • changedInput schema / properties / kind / description
      Previous value: -"One of wrong_fact, broken_tool, missing_tool, idea."New value: +"Type of report: a wrong dated figure, a broken tool, a missing tool or an idea."
    • changedInput schema / properties / summary / description
      Previous value: -"What went wrong or the idea, in one or two sentences, with no personal details."New value: +"The problem or idea in one or two general sentences, without personal details."
  2. Changed4 schema fields changed
    • changedInput schema / properties / details / description
      Previous value: -"Optional: what was asked of the tool (in general words), what it returned and what the official source says instead"New value: +"What was asked, what came back, and what the official source says, in general words."
    • changedInput schema / properties / kind / description
      Previous value: -"wrong_fact: an answer had a wrong or outdated fact. broken_tool: a tool failed or acted oddly. missing_tool: a tool or data Divux should have. idea: anything else."New value: +"One of wrong_fact, broken_tool, missing_tool, idea."
    • changedInput schema / properties / summary / description
      Previous value: -"What went wrong or what you suggest, in one or two sentences, with no personal details"New value: +"What went wrong or the idea, in one or two sentences, with no personal details."
    • changedInput schema / properties / tool / description
      Previous value: -"The Divux tool involved, by name (e.g. check_food), when there was one"New value: +"Name of the Divux tool involved, when one was involved."
  3. Added

TDQS

A4.5/5.0
Behavior5/5

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

Well beyond the annotations (which only flag it as a non-read-only write), the description discloses retention ('Divux keeps the text'), the absence of any reply, the 'stored as sent' nature of the text, a personal-details advisory, and a concrete rate limit of 5 reports/day per connection. These are exactly the operational facts an agent must know before invoking a submission tool.

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 the core purpose and the kind taxonomy; every sentence carries information about storage, privacy, or limits. The final sentence is partly redundant with the opening ('Applies to questions about reporting a problem with Divux'), which keeps it from a 5.

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 4-parameter write tool with no output schema, the description covers inputs, privacy handling, retention, and rate limits. The one gap is that it never says what a successful call returns or how failure (e.g. daily limit hit) is surfaced, leaving the agent to infer the response shape.

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 earns above that by restating field intent compactly and adding a cross-cutting constraint the schema does not encode ('text is stored as sent, so the fields are for general descriptions without personal details'). It still duplicates the length limits verbatim rather than adding new semantics.

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 ('Stores a short report for Divux') and immediately enumerates the four report categories that map to the kind enum. No sibling tool shares this purpose — all check_*/compare_*/plan_* tools are read/query tools, so the distinction is unambiguous.

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?

The closing sentence explicitly frames the applicable case ('questions about reporting a problem with Divux or suggesting an idea to Divux'), which is clear trigger guidance. It stops short of naming when not to use it or pointing at alternatives, but given the sibling set is purpose-disjoint, that omission is minor.

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

All divux toolsInspect
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