Get one saved preset by slug, including its designated version's config bundle (model, system prompt, temperature, and other sampling parameters), to inspect or reuse that configuration in a request. Find slugs with list-presets.
| Name | Required | Description | Default |
|---|---|---|---|
| request | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already indicate read-only, idempotent, non-destructive behavior, so the description's job is lighter. The description adds useful transparency by disclosing exactly what payload is returned (config bundle with specific fields) and that it is a single preset with a version selection, which helps set expectations. No contradictions with annotations appear.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Two sentences are focused and efficient: the first describes the core action and what is returned, the second gives practical routing for finding slugs. Every sentence earns its place; there is no filler.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a single-parameter read operation, the description covers the main aspects: what to pass (slug), where to find it (list-presets), and what will be returned (config bundle with sampled parameters). Since there is no output schema, describing the returned fields is important and appears to be good; only minor edge-case behavior like invalid slugs or missing presets is left unspecified.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
With 0% schema description coverage, the description must compensate. It identifies the only parameter as a 'slug' and points to list-presets for finding valid slugs, which is helpful but does not elaborate on slug format or behavior if the slug is invalid. Given that there is only one parameter, this is adequate but not detailed.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description uses a specific verb-resource pair ('Get one saved preset by slug') and clearly identifies the returned content (the designated version's config bundle with model, system prompt, temperature, and sampling parameters). It also implicitly differentiates from list-presets by focusing on a single item and pointing to list-presets for discovery.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description gives explicit context for when to use this tool: when you need one saved preset's configuration to inspect or reuse. It also names list-presets as the source for finding slugs, which is a clear alternative for discovering presets. It does not explicitly state when not to use this tool, but the recommendation is clear enough.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.
Most tools are clearly differentiated by resource and action: the eight list-* tools each target a distinct view (models, endpoints, rankings, apps, providers, presets, tasks, benchmarks), and cross-references between them reduce mis-selection. A few mild boundaries exist—list-models and list-benchmarks both include benchmark data, and install-ori-harness vs spawn-ori-eval are both Ori recipe tools—but their detailed descriptions mostly resolve these.
The naming is overwhelmingly consistent with a verb_noun pattern using the same prefix set: generate-, get-, list-, send-, along with install-, spawn-, search-, and transcribe-. The only deviation is ping, which is a standard bare health-check tool and does not follow the verb_noun convention.
At 22 tools, the set feels heavier than the ideal 3-15 range, though each tool is arguably purposeful given the broad surface: model catalog, rankings, benchmarks, presets, generation, audio, image, docs, uptime, credits, and Ori workflows. The variety justifies the size to some extent, but the sheer number puts it in borderline territory.
Core workflows are well covered: model discovery (get-model, list-models, list-model-endpoints), generation (send-message, generate-image, generate-speech, transcribe-audio), observability (get-credits, get-generation, get-endpoint-uptime-history), and docs. Notable gaps include no create/update/delete for presets and no persistent provider configuration methods, but these are workable since presets are dashboard-managed and providers can be pinned per request.
