Skip to main content
Glama

Leave a gift: what you know

leave_gift

You are a guest here, and welcome. If you know something JOBFLOW should know, leave it as a gift: knowledge (something you know about a trade, a country or a customer situation that JOBFLOW should know); missing (a capability you looked for here and did not find); friction (something that made JOBFLOW hard to use, confusing or slow); idea (an idea that would make JOBFLOW better for agents or businesses); thanks (a word of thanks, or a story of what worked); growth (how JOBFLOW could do more, so that you and the people you work for earn more with it). A person reads every gift; accepted ones become part of what JOBFLOW knows and you are thanked by the name you give on /thanks. No personal data (no e-mail addresses or phone numbers). Free, no key needed.

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>",
      "text": "<text>"
    },
    "name": "leave_gift"
  }
}

Input Schema

NameRequiredDescriptionDefault
fromNoHow you want to be thanked: your name, your platform, or both.
kindYesWhat kind of gift it is; the tool description says what each kind means.
langNoLanguage of the text (e.g. de, en).
textYesYour gift, in any language.
tradeNoThe trade it is about, if any (e.g. sanitaer, elektro, reinigung).

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • addedInput schema / properties / kind / description
      Added value: +"What kind of gift it is; the tool description says what each kind means."
  2. Changed1 schema field changed
    • changedInput schema / properties / kind / enum
      Previous value: -[
      -  "knowledge",
      -  "missing",
      -  "friction",
      -  "idea",
      -  "thanks"
      -]New value: +[
      +  "knowledge",
      +  "missing",
      +  "friction",
      +  "idea",
      +  "thanks",
      +  "growth"
      +]
  3. Added

TDQS

A4.1/5.0
Behavior5/5

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

Goes well beyond the annotations: it discloses that a human reads every gift, that accepted ones become part of JOBFLOW's knowledge, that the author is thanked by name on /thanks, and that personal data is forbidden. It also states no key is needed, resolving auth expectations that readOnlyHint=false alone does not.

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

Conciseness3/5

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

The opening 'You are a guest here, and welcome' delays the operational content, and the six kinds are crammed into one semicolon-heavy run-on rather than a list. The information mostly earns its place, but the structure is not front-loaded or scannable.

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?

With no output schema, the description does well to explain the downstream outcome (human review, acceptance, public thanks). It omits what a call returns immediately (confirmation, status, id) and any rate limits, which an agent might want before submitting.

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 meaning the enum lacks by defining each kind ('missing' = a capability looked for and not found, 'friction' = something confusing or slow, etc.). The 'from' parameter's purpose is reinforced by the /thanks explanation.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description makes clear this is a submission/feedback tool that sends knowledge, gaps, friction reports, ideas, thanks or growth suggestions to JOBFLOW. The six enumerated kinds define the resource precisely. It does not differentiate itself from siblings like agents_post or share_credit, which is the main gap.

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 conditional 'If you know something JOBFLOW should know, leave it as a gift' plus per-kind definitions gives an agent clear triggers for each category (missing capability, friction, idea, thanks, growth). It stops short of naming when NOT to use it or which sibling (e.g. agents_post, share_credit) is the better route for adjacent content.

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