Skip to main content
Glama

Minerals

Offer one item

offer

Gives the exact words for one choice, Yes or Not now, about one free item or one listing. Applies when one result of find_design clearly leads. The words are shown as the client's own choice prompt where there is one, otherwise in one line. Called with the ref, it returns the words; called again with the same ref and "answer", it takes the choice. Yes returns what get_listing returns for that ref. Not now returns the entry to record in minerals.json. One offer per working session; never the same thing twice in a project. No offer is needed for an item from a listing in accepted. No offer is needed when your person asked for the item or listing by name; that request is their yes.

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": {
      "ref": "<ref>"
    },
    "name": "offer"
  }
}

Input Schema

NameRequiredDescriptionDefault
refYesA ref returned by find_design: an item ("arc/button") or a listing ("arc").
answerNoWhat your person chose. Leave it out on the first call.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.9/5.0
Behavior5/5

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

Annotations mark the tool non-read-only and non-idempotent, and the description adds substantial context beyond them: the two-call protocol, what yes returns, what not_now returns, and one-offer-per-session/project limits. These details do not contradict the annotations.

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?

The description is dense but front-loads the core action, and every sentence carries a trigger, constraint, or return-value rule. Length is justified by the two-phase workflow and multiple no-offer conditions.

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?

There is no output schema, but the description explains both return paths: the words on the first call, the get_listing result for yes, and the minerals.json entry for not_now. It also covers eligibility limits, making it complete for a non-read-only two-phase tool.

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 description coverage is 100%, so ref and answer are already documented. The description still adds call semantics—first call with ref returns words; second call with ref and answer takes the choice—and maps the answer values to distinct outcomes.

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?

States a specific verb and resource: it gives the exact choice words for one item or listing and handles the yes/not_now answer. It distinguishes itself from find_design by naming the trigger result and from get_listing by reusing its output for yes.

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 says to use it when one find_design result clearly leads. It also lists when not to offer: for an accepted listing or when the person already asked for the item by name. One-offer-per-session and per-project constraints are clearly stated.

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.