Skip to main content
Glama

Datoka Hooks

by dev.workers.bhazarstudio.datoka-hooks-test
OverviewDiscussionsAdmin

Accept Hook Event

accept_hook_event
Idempotent

Enqueue up to 65536 payload bytes for a previously verified receiver using its delivery token. Returns a deliveryId, not proof of delivery. Reuse eventId and exact bytes on retries, then poll get_hook_delivery. The free allowance is 100 events/day per verified receiver; extra admissions consume purchased credits. No arbitrary destination can be supplied here.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
tokenYesPrivate delivery token returned by registration; authenticates event submission, delivery lookup and receipt verification for this hook.
hookIdYesHook identifier returned by registration; preserve for all subsequent operations.
eventIdYesStable caller-chosen event identifier, for example order-20261007-01. Reuse with identical payload bytes on retry; different bytes under the same ID are rejected.
bodyBase64YesCanonical base64 payload, at most 65536 decoded bytes. Preserve exact bytes with eventId on retries.
contentTypeYesMedia type of the decoded payload bytes; JSON must be encoded as UTF-8 before base64 conversion.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed3 schema fields changed
    • addedInput schema / properties / contentType / description
      Added value: +"Media type of the decoded payload bytes; JSON must be encoded as UTF-8 before base64 conversion."
    • addedInput schema / properties / eventId / description
      Added value: +"Stable caller-chosen event identifier, for example order-20261007-01. Reuse with identical payload bytes on retry; different bytes under the same ID are rejected."
    • changedInput schema / properties / token / description
      Previous value: -"Private 32-byte secret encoded as 64 lowercase hexadecimal characters. Never expose in logs."New value: +"Private delivery token returned by registration; authenticates event submission, delivery lookup and receipt verification for this hook."
  2. Changed4 schema fields changed
    • 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 / bodyBase64 / description
      Added value: +"Canonical base64 payload, at most 65536 decoded bytes. Preserve exact bytes with eventId on retries."
    • addedInput schema / properties / hookId / description
      Added value: +"Hook identifier returned by registration; preserve for all subsequent operations."
    • addedInput schema / properties / token / description
      Added value: +"Private 32-byte secret encoded as 64 lowercase hexadecimal characters. Never expose in logs."
  3. First observed

TDQS

A4.6/5.0
Behavior5/5

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

Goes well beyond the annotations: it clarifies the return is a deliveryId and not proof of delivery, that the free allowance is 100 events/day per receiver with credits consumed beyond that, and that identical bytes are required under a reused eventId. Annotations cover the safety/idempotency profile, and the description adds quota, retry, and delivery-semantics context that the annotations do not.

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 action and payload bound, then retry/quota behavior. Dense but every clause carries an operational constraint; no filler.

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?

With no output schema, the description correctly explains what comes back (deliveryId, not delivery proof), how to observe real delivery (poll get_hook_delivery), quota/credit implications, and retry idempotency. An agent has everything needed to call it correctly.

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 real meaning: the 65536-byte payload ceiling, the retry invariant tying eventId to exact bytes, and the role of the token as a delivery credential. It stops short of explaining contentType encoding rules, which remain schema-only.

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 with scope: enqueue payload bytes for a previously verified receiver via its delivery token. It is clearly distinguishable from siblings like register_destination or purchase_hook_credits, and the '(receiver)' qualifier pins down what is being acted on.

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 explicit operational flow: reuse eventId and exact bytes on retries, then poll get_hook_delivery, and rules out supplying an arbitrary destination. It names a follow-up sibling but does not contrast against other siblings (e.g., verify_hook_receipt) or state when this tool should not be called.

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

All Datoka Hooks toolsInspect
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