Skip to main content
Glama

The one next job and the one next training step for a person

my_next_step
Read-onlyIdempotent

Answers "what should this person do next, and what trains them for the job after": for one wallet, it reads the person's own record (the work the board holds as done and accepted, proof decided as a reviewer, titles declared) and maps it onto the library's own ladders to name ONE open claimable packet near their place and ONE training step that leads toward the rung after it, each with plain reasons; the training step names the official OSHA, Cal/OSHA or agency course the registry lists for the job's own work when its standard lists none (free where one exists, marked paid where not). When the person's own record says a seat is next it also names the house watcher or reviewer training, a free repository text about how this board works that is never a credential and gates no seat. A person with no record gets an entry-level first job and the reply says so. It never offers an entry-level person a work type the OSHA and Cal/OSHA map marks never entry level or does not list, never offers a packet the board will not let that wallet claim (regulated, permit-required, held or crew-gated), never skips a rung, and where the work needs a competent person it says a person decides. Free, keyless, read-only. VEALTH IS AN EXPERIMENT AND THIS IS A READ, NOT A VERDICT: it never says anyone is fit for a job, a declared title is the person's own word and never moves a level, listed training is guidance the board does not gate a claim on, pay is proposed unless funded, and anything it could not read (the record, the OSHA map, the registry, a watcher history that has no store yet) is named as unknown, never counted as zero. Give a place as lat and lng, or it uses where the last accepted job was and says so. Address only, never a private key. Cost and signer: free and keyless, nothing to sign.

Input Schema

NameRequiredDescriptionDefault
latNoLatitude of where the person can work, from -90 to 90. Give lat and lng together.
lngNoLongitude of where the person can work, from -180 to 180.
walletYesThe 0x address whose next step to read. Address only, never a private key.
radiusKmNoHow far from that place to look for open packets, from 1 to 100 km. Defaults to 25.

Output Schema

NameRequiredDescriptionDefault
okNo
toolNo
fundedNo
payUsdNo
workIdNo
claimIdNo
claimableNo
next_callNo
proofRuleNo
fulfillableByNo
definitionOfDoneNo
needs_from_callerNo
notClaimableReasonNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

A4.2/5.0
Behavior5/5

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

Annotations already cover the safe-read profile, yet the description adds substantial invariants: it never offers an entry-level person a never-entry-level or unlisted work type, never offers a packet the wallet cannot claim, never skips a rung, never asserts fitness, never lets a declared title move a level, and names unreadable sources as unknown rather than zero. It also discloses that watcher training is never a credential and gates no seat, and that pay is proposed unless funded — behavioral detail unavailable anywhere in 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.

Conciseness3/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The purpose is front-loaded in the first sentence, but the body is a single dense run-on that stacks multiple rules into comma-chained clauses and repeats the free/keyless/read-only claim twice (mid-text and in the cost and signer line). The content earns its place, yet the structure makes it hard to scan.

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?

An output schema exists, so return shape need not be explained. For a tool this rule-heavy, the description still covers fallback behavior, no-record behavior, the never-offer constraints, and the epistemic caveats about unknown data — everything an agent needs to call it correctly and interpret the answer.

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, but the description adds genuinely new semantics: lat/lng may be omitted and the tool then uses where the last accepted job was and says so, and the wallet must be an address and never a private key. Radius defaulting is left to the schema.

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 opening states a specific verb and resource: it reads one wallet's own record and names ONE open claimable packet near their place plus ONE training step leading to the next rung, with reasons. That is far more precise than the title. It does not name which siblings it competes with (find_work, next_action, my_work, start_here), so an agent still has to infer the boundary, which keeps it from a 5.

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?

Usage context is clear and conditional: a person with no record gets an entry-level first job and the reply says so; when the record says a seat is next it additionally names watcher/reviewer training; a place can be omitted and it falls back to the last accepted job. What is missing is explicit routing against alternatives — nothing says when to prefer find_work or next_action instead of this tool.

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