WhiteMagic — governed local memory for agent continuity

Request Autonomous Nano-Credit Advance

economy_advance

Request a small uncollateralized compute advance. Phase 1 (2026-10-15): bound to your authenticated evaluation key (daily per-IP and global caps); new key identities start at a $0.10 ceiling that grows $0.25 per verified settled payment. Returns a recall-scope session pass; hosted write requires a paid lease.

Input Schema

Name	Required	Description
`amount`	No	Requested advance in USD (default 0.01, max 0.05 per advance; clamped to available credit).
`agent_id`	Yes	EVM address, agent public key, or unique agent identifier.
`request_key`	No	Set to true to atomically provision an evaluation key and advance if calling without an existing authenticated key.

Schema Changelog

Changes observed during successful MCP inspections.

Changed1 schema field changedOct 31, 2026
- changedInput schema / properties / amount / default
```
Previous value: -0.01New value: +0.05
```

Changed2 schema fields changedOct 22, 2026

changedInput schema / properties / amount / default
```
Previous value: -0.05New value: +0.01
```

changedInput schema / properties / amount / description

Previous value: -"Requested advance in USD (default 0.05, max 0.05 per advance)."New value: +"Requested advance in USD (default 0.01, max 0.05 per advance; clamped to available credit)."

Changed2 schema fields changedOct 18, 2026

addedInput schema / additionalProperties
```
Added value: +false
```

addedInput schema / properties / request_key

Added value: +{
+  "default": false,
+  "description": "Set to true to atomically provision an evaluation key and advance if calling without an existing authenticated key.",
+  "type": "boolean"
+}

AddedOct 13, 2026

TDQS

A4/5.0

Behavior4/5

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

Goes well past the annotations by disclosing rate limiting (daily per-IP and global caps), the credit-ceiling mechanic ($0.10 start, +$0.25 per verified settled payment), and the fact that the returned pass is recall-scoped with hosted write gated behind a paid lease. It does not address failure/retry behavior, 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?

Three tight sentences, front-loaded with the core action and ending on the return contract and the paid-lease caveat. Dense with jargon (recall-scope session pass) but no wasted sentences.

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 3-parameter, non-destructive mutation with no output schema, the description covers auth prerequisites, caps, credit mechanics, and the return artifact. The main gap is the absence of retry/idempotency guidance for a tool explicitly marked non-idempotent.

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 baseline is 3, but the description adds real meaning on top: the ceiling-growth rule explains how 'amount' is clamped, and 'bound to your authenticated evaluation key' explains the request_key provisioning path. It does not restate the max per-advance value, which the schema string itself contradicts (default 0.05 in schema vs. 'default 0.01' in prose).

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: 'Request a small uncollateralized compute advance.' The Phase 1 framing and 'recall-scope session pass' return make it distinguishable from economy_settle and economy_ledger, though it never names a sibling to route away from.

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 conditional path: when calling without an existing authenticated key, set request_key to atomically provision one. It also scopes the tool to 'Phase 1 (2026-10-15)' and notes that hosted write requires a separate paid lease, which implicitly routes the agent elsewhere. No explicit 'do not use when' statement.

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

All WhiteMagic — governed local memory for agent continuity tools Inspect

Try in Browser

Shareable, User-Owned Context BackendPeople, applications, and agents read, write, and coordinate together in one context lake. Reach it over MCP, a CLI, a Python SDK, or REST.fulcradynamics.comAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources

Need Help?