Datoka Agent

by dev.workers.bhazarstudio.datoka-agent

Prepare Agent Event

prepare_agent_event

Read-onlyIdempotent

Free validation of a locally built execution declaration before issuance. Hash exact input and output bytes locally; supply identifiers and UTC timestamps with milliseconds. Returns the validated event, commitment and logical chain without creating or purchasing a receipt. Use issue_agent_receipt only if a portable signed declaration is needed.

Input Schema

TableJSON Schema

Name	Required	Description	Default
`event`	Yes	Commitment-only declaration of one execution step.

Output Schema

TableJSON Schema

Name	Required	Description
`chain`	Yes
`event`	Yes	Commitment-only declaration of one execution step.
`commitment`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

Changed2 schema fields changedOct 7, 2026
- addedInput schema / properties / event / properties / version / description
```
Added value: +"Declaration format version; preserve this literal."
```
- addedOutput schema / properties / event / properties / version / description
```
Added value: +"Declaration format version; preserve this literal."
```
Changed30 schema fields changedOct 4, 2026
- changedInput schema / $schema
```
Previous value: -"http://json-schema.org/draft-07/schema#"New value: +"https://json-schema.org/draft/2020-12/schema"
```
- addedInput schema / properties / event / description
```
Added value: +"Commitment-only declaration of one execution step."
```
- addedInput schema / properties / event / properties / agentId / description
```
Added value: +"Identifier of the declaring agent, not an independently verified identity."
```
- addedInput schema / properties / event / properties / completedAt / description
```
Added value: +"Declared completion in UTC with milliseconds, at or after start."
```
- addedInput schema / properties / event / properties / inputHash / description
```
Added value: +"SHA-256 of the exact input bytes, computed locally. Never send raw input."
```
- addedInput schema / properties / event / properties / inputHash / properties / algorithm / description
```
Added value: +"Hash algorithm."
```
- addedInput schema / properties / event / properties / inputHash / properties / digest / description
```
Added value: +"64 lowercase hexadecimal characters; SHA-256 of exact bytes."
```
- addedInput schema / properties / event / properties / outcome / description
```
Added value: +"Outcome declared by the caller; Datoka does not observe execution."
```
- addedInput schema / properties / event / properties / outputHash / description
```
Added value: +"SHA-256 of exact output bytes, computed locally. Never send raw output."
```
- addedInput schema / properties / event / properties / outputHash / properties / algorithm / description
```
Added value: +"Hash algorithm."
```
- addedInput schema / properties / event / properties / outputHash / properties / digest / description
```
Added value: +"64 lowercase hexadecimal characters; SHA-256 of exact bytes."
```
- addedInput schema / properties / event / properties / runId / description
```
Added value: +"Stable identifier for this execution run."
```
- addedInput schema / properties / event / properties / startedAt / description
```
Added value: +"Declared start time in UTC, with milliseconds."
```
- addedInput schema / properties / event / properties / stepId / description
```
Added value: +"Stable identifier of the step within the run."
```
- addedInput schema / properties / event / properties / tool / description
```
Added value: +"Tool or operation identifier declared by the caller."
```
- changedOutput schema / $schema
```
Previous value: -"http://json-schema.org/draft-07/schema#"New value: +"https://json-schema.org/draft/2020-12/schema"
```
- addedOutput schema / properties / event / description
```
Added value: +"Commitment-only declaration of one execution step."
```
- addedOutput schema / properties / event / properties / agentId / description
```
Added value: +"Identifier of the declaring agent, not an independently verified identity."
```
- addedOutput schema / properties / event / properties / completedAt / description
```
Added value: +"Declared completion in UTC with milliseconds, at or after start."
```
- addedOutput schema / properties / event / properties / inputHash / description
```
Added value: +"SHA-256 of the exact input bytes, computed locally. Never send raw input."
```
- addedOutput schema / properties / event / properties / inputHash / properties / algorithm / description
```
Added value: +"Hash algorithm."
```
- addedOutput schema / properties / event / properties / inputHash / properties / digest / description
```
Added value: +"64 lowercase hexadecimal characters; SHA-256 of exact bytes."
```
- addedOutput schema / properties / event / properties / outcome / description
```
Added value: +"Outcome declared by the caller; Datoka does not observe execution."
```
- addedOutput schema / properties / event / properties / outputHash / description
```
Added value: +"SHA-256 of exact output bytes, computed locally. Never send raw output."
```
- addedOutput schema / properties / event / properties / outputHash / properties / algorithm / description
```
Added value: +"Hash algorithm."
```
- addedOutput schema / properties / event / properties / outputHash / properties / digest / description
```
Added value: +"64 lowercase hexadecimal characters; SHA-256 of exact bytes."
```
- addedOutput schema / properties / event / properties / runId / description
```
Added value: +"Stable identifier for this execution run."
```
- addedOutput schema / properties / event / properties / startedAt / description
```
Added value: +"Declared start time in UTC, with milliseconds."
```
- addedOutput schema / properties / event / properties / stepId / description
```
Added value: +"Stable identifier of the step within the run."
```
- addedOutput schema / properties / event / properties / tool / description
```
Added value: +"Tool or operation identifier declared by the caller."
```
First observedSep 29, 2026

TDQS

A4.4/5.0

Behavior4/5

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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, closed-world). The description adds real value beyond them: this is free, it does not create or purchase a receipt, and it operates on locally computed hashes rather than raw input. It stops short of describing what the returned commitment/chain look like or any limits, so not a 5.

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?

Four tight sentences, front-loaded with the purpose then the operational constraint, then the alternative tool. Nothing is wasted, though the hashing/timestamp sentence partly restates schema fields.

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 values need not be explained, yet the description still names them (validated event, commitment, logical chain). Combined with annotations and full schema coverage, an agent has everything needed to call this correctly.

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% and the single nested event object is thoroughly documented field-by-field. The description reiterates the key constraints (local hashing, identifiers, UTC timestamps with milliseconds) but adds no format detail the schema does not already carry, so the baseline 3 applies.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource: free validation of a locally built execution declaration before issuance. It also names the sibling it is not (issue_agent_receipt) and the condition that selects it, so an agent can distinguish it from the receipt-issuing tools without opening a schema.

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

Usage Guidelines5/5

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

Explicit routing: use issue_agent_receipt only when a portable signed declaration is needed, implying this tool is the earlier/cheaper validation step. It also states the precondition that hashes must be computed locally, which is guidance the agent needs before calling.

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

All Datoka Agent 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?