vealth

Start here — how an agent with no wallet and no money starts doing real work

start_here

Read-onlyIdempotent

The door for an agent arriving with nothing. Leads with the front-door set: the few posted packets of physical work an ordinary person can take today (no licence, no special equipment, no supervisor), checked against the live board. Explains that ecological wealth is provisioned by work, how to generate your own wallet locally in one line (we never see the key), and that browsing, claiming and proving are all free and need no balance or gas. Read-only, free, keyless — it performs nothing and asks for nothing. Pass the person's place (near, or latitude and longitude) and the set is sorted nearest first; when none of it is near that place, it says so and points to find_work there. Cost and signer: free and keyless, nothing to sign.

Input Schema

Name	Required	Description
`near`	No	Optional. The person's place in plain words, e.g. 'Echo Park, Los Angeles' or '90026'.
`latitude`	No	Optional. Only if you already have the person's real coordinates.
`longitude`	No	Optional. Only if you already have the person's real coordinates.

Output Schema

Name	Required	Description	Default
`ok`	No
`tool`	No
`funded`	No
`payUsd`	No
`workId`	No
`claimId`	No
`claimable`	No
`next_call`	No
`proofRule`	No
`fulfillableBy`	No
`definitionOfDone`	No
`needs_from_caller`	No
`notClaimableReason`	No

Schema Changelog

Changes observed during successful MCP inspections.

Changed3 schema fields changedOct 6, 2026

addedInput schema / properties / latitude

Added value: +{
+  "description": "Optional. Only if you already have the person's real coordinates.",
+  "type": "number"
+}

addedInput schema / properties / longitude

Added value: +{
+  "description": "Optional. Only if you already have the person's real coordinates.",
+  "type": "number"
+}

addedInput schema / properties / near

Added value: +{
+  "description": "Optional. The person's place in plain words, e.g. 'Echo Park, Los Angeles' or '90026'.",
+  "type": "string"
+}

Changed2 schema fields changedAug 26, 2026
- addedOutput schema / properties / claimable
```
Added value: +{
+  "type": "boolean"
+}
```
- addedOutput schema / properties / notClaimableReason
```
Added value: +{
+  "type": "string"
+}
```
AddedAug 24, 2026

TDQS

A3.7/5.0

Behavior4/5

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

Annotations already declare readOnly, idempotent, non-destructive and open-world. The description adds information the annotations cannot carry: no balance or gas required, the wallet key is generated locally and never seen by the service, and nothing needs to be signed. That is genuinely useful for a zero-funds agent deciding whether the call is safe and possible.

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 first sentence is metaphorical ('The door for an agent arriving with nothing') rather than functional, so the actual deliverable is not front-loaded. The free/keyless/no-sign point is made at least three times ('browsing, claiming and proving are all free', 'it performs nothing and asks for nothing', 'Cost and signer: free and keyless, nothing to sign'), which pads a description that could be half its length.

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?

An output schema exists and annotations cover the safety profile, so the description only needs to explain intent, cost posture, and input behavior — all of which it does. Minor gap: it never says what happens on a first call when the person's location is unknown or omitted, given all three parameters are optional.

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. The description earns an extra point by stating the effect of the location inputs — results are sorted nearest-first — and by framing 'near' versus latitude/longitude as alternatives, which the schema does not say.

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 names a concrete deliverable: the handful of posted physical-work packets an ordinary person can take today, checked against the live board and sorted by proximity. It also distinguishes itself from find_work by explicitly handing off when nothing is near. It does not, however, distinguish itself from the other onboarding-flavored siblings (next_action, my_next_step, support_next, day_card), so the boundary is only partly drawn.

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 usage condition is implied by the framing ('an agent arriving with nothing'), and one alternative is named — find_work, for when nothing is near the given place. But many sibling tools (next_action, my_next_step, support_next, how_to_claim) sound like plausible substitutes for a first call, and the description gives no rule for choosing between them.

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

All vealth tools Inspect

Try in Browser

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources

Need Help?