Skip to main content
Glama

draw

Request units from a shared quota pool for an agent, returning an allow/deny decision, reason, and hash-chained receipt.

Instructions

Draw units from a pool for one agent. Returns allowed or denied, a reason, and a hash-chained receipt. Costs 1 credit per draw call, allowed or denied; an idempotency key replay is free.

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": {
      "pool_id": "<pool_id>",
      "agent_id": "<agent_id>",
      "units": "<units>"
    },
    "name": "draw"
  }
}

Input Schema

NameRequiredDescriptionDefault
unitsYes
pool_idYes
agent_idYes
idempotency_keyNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A3.9/5.0
Behavior4/5

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

With no annotations supplied, the description carries the full burden and does substantial work: it discloses the return shape (allowed/denied, reason, hash-chained receipt), the cost model (1 credit per call, charged even on denial), and the idempotency replay exception. It omits auth/permission requirements and whether denials arise from policy, balance, or pool capacity.

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?

Three short sentences, zero waste, with the core action front-loaded and the cost/idempotency caveats following. Every sentence carries distinct information.

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 mutation tool with no annotations and no output schema, the definition covers the essential behavior: outcome values, cost, and idempotency. Remaining gaps are failure semantics (e.g., whether an exhausted pool returns denied with a reason versus an error) and authorization requirements.

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 0%, so the description must compensate, and it does so conceptually for all four parameters: the pool being drawn from, the single agent, the units, and the idempotency key with its replay semantics. It still gives no format or constraint detail, such as whether units may be fractional, a maximum draw size, or key format.

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 ('Draw units from a pool') plus the scope ('for one agent'), which is clearly distinct from pool administration siblings like create_pool, topup_pool, and get_pool. It does not explicitly name an alternative tool, so it stops short of full sibling routing.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The credit cost per call and the free idempotency replay implicitly tell the agent to reuse an idempotency key rather than re-draw, which is useful guidance. However, there is no explicit when-to-use/when-not statement and no named alternative for related needs such as checking balances or reading a prior receipt.

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