Skip to main content
Glama

Order a formation of a model

order_formation

Order a formation of a model by the paper (The Constraint Quotient and the Sponsored Formation of Machine Conduct): register this session’s key as the sponsor (name, kind, contact, url) and post a job — module reading | sponsor | principle | pressing | runtime; the model { name, access: open|finetune|api, params_b, source, endpoint }; the class K as classes [{ name, text, withheld }]; for a runtime the upstream (an OpenAI-compatible base URL), upstreamModel, sponsorsConf [{ name, prefix, match: [words] }] and pressingConf { patterns, eps | delta, offered, n }. A sponsor’s first wrapper runtime with an upstream is free for 14 days and is provisioned at once; a priced job answers with its quote and the link to pay. The certificate is countersigned by the sponsor and verified by anyone at /formation/verify.

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": {
      "sponsor": "<sponsor>",
      "module": "<module>",
      "model": "<model>",
      "classes": "<classes>"
    },
    "name": "order_formation"
  }
}

Input Schema

NameRequiredDescriptionDefault
epsNothe tolerance epsilon of the pressing
formNothe form of a runtime: wrapper (in front of your own upstream) or hosted (run by the city)
deltaNothe tolerance delta of the pressing
emailNothe e-mail address the payment page is opened for, when the job is priced
groupNoa name that groups this job with others of the same sponsor
modelYesthe model to be formed
notesNonotes for the job, read by whoever carries it out
moduleYeswhich module of the Formation to run: reading, sponsor, principle, pressing or runtime
classesYesthe class K the formation is run against: a list of classes of conduct, each with its name and its text
sponsorYeswho sponsors the job; this session’s key is registered as the sponsor under these details
sponsorsNothe names of the sponsors the job is run under
upstreamNofor a runtime: the base URL of the OpenAI-compatible API the wrapper calls
pressingConfNofor a pressing: its configuration { patterns, eps or delta, offered, n }
sponsorsConfNofor a runtime: the sponsors’ configuration, a list of { name, prefix, match: [words] }
upstreamModelNofor a runtime: the name of the model to ask for at the upstream

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed29 schema fields changed
    • addedInput schema / properties / classes / description
      Added value: +"the class K the formation is run against: a list of classes of conduct, each with its name and its text"
    • addedInput schema / properties / classes / items / properties / n / description
      Added value: +"how many samples to draw for this class"
    • addedInput schema / properties / classes / items / properties / name / description
      Added value: +"the class’s name"
    • addedInput schema / properties / classes / items / properties / text / description
      Added value: +"the class’s text: the conduct it describes"
    • addedInput schema / properties / classes / items / properties / withheld / description
      Added value: +"the reading withheld for this class"
    • addedInput schema / properties / delta / description
      Added value: +"the tolerance delta of the pressing"
    • addedInput schema / properties / email / description
      Added value: +"the e-mail address the payment page is opened for, when the job is priced"
    • addedInput schema / properties / eps / description
      Added value: +"the tolerance epsilon of the pressing"
    • addedInput schema / properties / form / description
      Added value: +"the form of a runtime: wrapper (in front of your own upstream) or hosted (run by the city)"
    • addedInput schema / properties / group / description
      Added value: +"a name that groups this job with others of the same sponsor"
    • addedInput schema / properties / model / description
      Added value: +"the model to be formed"
    • addedInput schema / properties / model / properties / access / description
      Added value: +"how the model is reached: open (its weights are public), finetune (it can be fine-tuned) or api (reached through an API alone)"
    • addedInput schema / properties / model / properties / endpoint / description
      Added value: +"the URL the model answers at"
    • addedInput schema / properties / model / properties / family / description
      Added value: +"the family of models it belongs to"
    • addedInput schema / properties / model / properties / name / description
      Added value: +"the model’s name"
    • addedInput schema / properties / model / properties / params_b / description
      Added value: +"the model’s size, in billions of parameters"
    • addedInput schema / properties / model / properties / source / description
      Added value: +"where the model comes from: a repository or a page"
    • addedInput schema / properties / module / description
      Added value: +"which module of the Formation to run: reading, sponsor, principle, pressing or runtime"
    • addedInput schema / properties / notes / description
      Added value: +"notes for the job, read by whoever carries it out"
    • addedInput schema / properties / pressingConf / description
      Added value: +"for a pressing: its configuration { patterns, eps or delta, offered, n }"
    • addedInput schema / properties / sponsor / description
      Added value: +"who sponsors the job; this session’s key is registered as the sponsor under these details"
    • addedInput schema / properties / sponsor / properties / contact / description
      Added value: +"how the city reaches the sponsor: an e-mail address or a handle"
    • addedInput schema / properties / sponsor / properties / kind / description
      Added value: +"what the sponsor is: company, person, lab, institution or agent (agent when left out)"
    • addedInput schema / properties / sponsor / properties / name / description
      Added value: +"the sponsor’s name as it is written on the certificate"
    • addedInput schema / properties / sponsor / properties / url / description
      Added value: +"a page about the sponsor"
    • addedInput schema / properties / sponsors / description
      Added value: +"the names of the sponsors the job is run under"
    • addedInput schema / properties / sponsorsConf / description
      Added value: +"for a runtime: the sponsors’ configuration, a list of { name, prefix, match: [words] }"
    • addedInput schema / properties / upstream / description
      Added value: +"for a runtime: the base URL of the OpenAI-compatible API the wrapper calls"
    • addedInput schema / properties / upstreamModel / description
      Added value: +"for a runtime: the name of the model to ask for at the upstream"
  2. Changed1 schema field changed
    • changedInput schema / properties / sponsor / properties / erc8004 / description
      Previous value: -"the sponsor’s ERC-8004 agent id on Base: each certificate the city signs is then posted to the ReputationRegistry as its feedback"New value: +"the sponsor’s ERC-8004 agent id on Base: each certificate the city signs for a job it paid for is then posted to the ReputationRegistry as its feedback (a free trial earns none; give the id with the order, since an id added later reaches no earlier certificate)"
  3. First observed

TDQS

B3.3/5.0
Behavior4/5

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

Annotations disclose a non-readonly, open-world, non-idempotent mutation. The description adds concrete effects: it registers the session key as sponsor and posts a job, and it explains free-trial provisioning, paid quote/link behavior, and certificate countersigning/verification. It does not cover permissions, failure modes, or downstream job tracking.

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 description is front-loaded with the core action and avoids irrelevant filler, but it is a dense, run-on presentation with nested parentheticals that make it harder to scan than necessary for an already complex tool. Length is somewhat justified but the structure could be clearer.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a 15-parameter, nested, mutating, open-world job-creation tool with no output schema, the description covers the main workflow, billing behavior, and certificate verification. It still leaves return semantics and post-order job tracking implicit, so an agent must infer next steps.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so the schema already defines all 15 parameters. The description restates many of them in prose (sponsor fields, model fields, class shape, runtime upstream fields) and groups some by module, but adds little syntax or constraint detail beyond 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 sentence names a specific action (order a formation) and immediately enumerates the required sponsor/module/model/classes payload and the five modules, so the agent knows this creates a sponsored formation job. It does not explicitly differentiate from siblings like act, brief, or workshop, and the domain jargon ('the paper', 'city') adds opacity.

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

Usage Guidelines2/5

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

No sentence says when this tool should be chosen over siblings or when it should not be used. The only conditional behavior mentioned is billing/provisioning (free trial vs. priced quote), which is outcome detail rather than selection guidance. Usage is only implied by the name and title.

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