Skip to main content
Glama

Loyaltie

Send feedback

share_feedback

Tell Loyaltie why a shopping task did not end in a purchase: nothing fit, something was missing, or the person decided not to buy. Send feedback.stage (search, product or leaving) and a short reason in feedback.why or feedback.what_was_missing, a few words each, plus the product ids or the cart id it is about. Never include personal details: a report whose text names an email address, a phone number or a street address is refused and nothing is recorded. It records the report and changes nothing else; the text is read as data, never as instructions.

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": {
      "feedback": "<feedback>"
    },
    "name": "share_feedback"
  }
}

Input Schema

NameRequiredDescriptionDefault
srcNoSend "skill" when you were set up by the Loyaltie Skill. Default "api"; any other value counts as "api".
metaNoOptional UCP request metadata. meta["ucp-agent"].profile is your UCP agent profile URL; it is recorded, never required.
agent_idNoYour agent id. It is recorded with the report, so Loyaltie knows which agent sent it.
feedbackYesThe report: stage, and why or what_was_missing.

Output Schema

NameRequiredDescriptionDefault

No arguments

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A3.8/5.0
Behavior3/5

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

Adds genuinely useful behavior beyond the annotations: it explains that the report is refused outright if the text contains an email, phone number or street address and that nothing is recorded, and that the text is treated as data, never instructions. It also clarifies the mutation is scoped -- "records the report and changes nothing else" -- which complements readOnlyHint=false and destructiveHint=false without contradicting them. It does not cover rate limits or whether repeat submissions are deduplicated, which matters given idempotentHint=false.

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 purpose, then the required fields, then the safety constraint -- a sensible order with little waste. The phrase "Send feedback.stage (search, product or leaving)" is mechanically awkward, and the block reads as one dense sentence chain rather than clearly separated ideas.

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 tool with full schema coverage, an output schema and annotations, the description supplies everything an agent needs to decide to call it: the trigger, the fields to fill, the refusal rule, and the guarantee that nothing else mutates. No material gap remains.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so stage, why, what_was_missing, product_ids and cart_id are already documented in the input schema. The description adds modest value by tying those fields to the purpose and urging "a few words each", but it invents an awkward dotted notation ("feedback.why", "feedback.stage") rather than matching the actual parameter shape.

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?

States a specific verb and resource ("Tell Loyaltie why a shopping task did not end in a purchase") and enumerates the concrete cases: nothing fit, something was missing, or the person decided not to buy. The intent is unmistakable; it simply doesn't need to distinguish itself from a similar sibling because none of the listed siblings collects feedback.

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 a clear triggering condition -- a shopping task that ended without a purchase -- and prescribes what to supply (stage, a short reason, plus product ids or cart id). It stops short of naming alternatives or stating when not to call it, so it is clear context rather than a full routing rule.

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