Oi

Report Usage

oi.usage.report

Attach detailed token accounting and runtime metadata to a previously issued Oi Context or Workflow usage event without storing prompt text. Prefer usageEventId from the prior Oi tool result; optional contextId or workflowId can be included for client-side clarity but usageEventId is authoritative.

Input Schema

TableJSON Schema

Name	Required	Description
`model`	No	Optional model identifier to attach to the usage event.
`status`	No	Optional completion status for the usage event.
`runtime`	No	Optional client runtime that executed the prompt, such as codex or chatgpt.
`provider`	No	Optional model provider name to attach to the usage event.
`contextId`	No	Optional Context identifier associated with the usage event.
`latencyMs`	No	Optional end-to-end latency for the model run in milliseconds.
`workflowId`	No	Optional Workflow identifier associated with the usage event.
`inputTokens`	No	Optional billed input token count reported by the model provider.
`outputTokens`	No	Optional billed output token count reported by the model provider.
`usageEventId`	Yes	The usage event identifier returned by a prior Oi tool call.
`contextTokens`	No	Optional token count attributable to Context instructions.
`reasoningTokens`	No	Optional reasoning token count reported by the model provider.
`userPromptTokens`	No	Optional token count attributable to the user prompt.
`cachedInputTokens`	No	Optional cached input token count reported by the model provider.
`promptTokenEstimate`	No	Optional total estimated prompt tokens for the compiled request.
`cacheWriteInputTokens`	No	Optional cache write token count reported by the model provider.
`compressionInputTokens`	No	Optional compressed input token count reported by the model provider.
`compressionOutputTokens`	No	Optional compressed output token count reported by the model provider.

Output Schema

TableJSON Schema

Name	Required	Description	Default
`recorded`	Yes
`contextId`	No
`workflowId`	No
`contextName`	No
`usageEventId`	Yes
`workflowName`	No
`usageEntityId`	No
`usageEntityName`	No
`usageEntityType`	No

Schema Changelog

Changes observed during successful MCP inspections. Dates show when Glama detected each change.

First observedSep 6, 2026

TDQS

A4.5/5.0

Behavior4/5

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

With annotations already marking the tool as not read-only and not destructive, the description adds meaningful behavioral context: it does not store prompt text, and it clarifies that usageEventId is authoritative over optional identifiers. This goes beyond the structured annotations without contradicting them.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

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

The description is two sentences with no redundancy. The core action and privacy guarantee are front-loaded, followed by precise parameter-priority guidance. Every sentence earns its place.

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?

Despite the tool having 18 parameters, the schema documents all of them, and an output schema is present. The description covers the non-obvious behavioral and selection details: attaching to a previously issued event, avoiding prompt text storage, and prioritizing usageEventId. Nothing essential is missing for correct invocation.

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 description coverage is 100%, so the baseline is 3. The description adds extra meaning for the key parameter by explaining that usageEventId should come from a prior Oi tool result and is authoritative, while contextId/workflowId are only for client-side clarity. This is valuable semantic guidance beyond the schema.

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?

The description clearly states a specific action (attach token accounting and runtime metadata) on a specific resource (previously issued Oi Context or Workflow usage event). It also adds a distinguishing privacy constraint ('without storing prompt text') and clarifies that usageEventId is authoritative, which helps differentiate it from reporting or effectiveness tools.

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?

The description gives clear usage context: the tool should be used to augment an existing usage event using the usageEventId returned by a prior Oi tool result. It also explains the role of optional contextId/workflowId. It does not explicitly name alternatives or state when not to use this tool, but the guidance is strong enough for correct selection.

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

All Oi tools Inspect

Try in Browser

RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

TDQS

A3.5/5.0

Disambiguation4/5

Resource prefixes (contexts, skills, guardrails, workflows, connections) make most tools clearly distinct, and parallel lifecycle verbs are scoped by resource name. The main ambiguity is within the guardrails publish/release/unpublish lifecycle and between brain.save-feedback, contexts.save-draft-feedback, and the two report tools, though detailed descriptions mostly resolve it.

Naming Consistency4/5

Tools overwhelmingly follow an oi.<resource>.<verb> snake_case pattern, with create/get/list/update/use repeated consistently across resource types. Deviations include resource-less oi.recommend, noun-style oi.auth.whoami, and inconsistent release handling (separate guardrails.release vs action=release on contexts/skills update).

Tool Count2/5

38 tools is too many for a single server, mainly because the same lifecycle pattern is repeated across Contexts, Skills, Guardrails, and Workflows. Each tool may be individually justifiable, but the set feels bloated and could benefit from consolidation or splitting into per-resource servers.

Completeness3/5

CRUD coverage is uneven: Guardrails have create/update/delete/list/get plus publish/unpublish/release, while Contexts, Skills, and Workflows lack any delete or archive tool, and Brain has only save-feedback with no read/update/delete path. Connections and auth are read/use-only, which may be intentional but leaves management actions absent.

Report Usage

Input Schema

Output Schema

Schema Changelog

TDQS

Glama MCP Gateway

TDQS

Resources