get_mana_creationReturn one published creation's public descriptive data and links. Never returns source code, bundles, or assets.
| Name | Required | Description | Default |
|---|---|---|---|
| slug | Yes | The creation's slug. | |
| handle | Yes | Creator handle, without the @. | |
| locale | No | BCP-47 locale for localized descriptions. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint, openWorldHint, idempotentHint, and non-destructive behavior. The description adds context beyond these by stating the return includes only public descriptive data and links, and by explicitly warning that source code, bundles, and assets are never returned. This gives the agent a clear boundary on response contents.
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?
The description is two concise sentences with no filler. The core behavior is front-loaded, and the negative boundary about source code/assets is a valuable addition that justifies its place.
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 simple read-only lookup tool with well-documented parameters and strong annotations, the description gives sufficient context: it identifies what is returned, what is not returned, and that only published creations are covered. There is no output schema, but 'public descriptive data and links' provides enough shape for an agent to understand the general response.
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?
Schema description coverage is 100%, so the parameters are already well documented. The description adds no additional parameter-specific meaning beyond what the input schema provides, but it doesn't need to because the schema already explains slug, handle, and locale.
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 states a specific verb ('Return'), a specific resource ('one published creation'), and clarifies the scope ('public descriptive data and links'). The second sentence explicitly excludes source code, bundles, and assets, which helps differentiate it from tools that might return creation content or binaries.
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 singular 'one' and 'published creation' imply this tool is for fetching a single creation's public metadata, as opposed to listing or searching creations. However, it does not explicitly name alternatives such as list_mana_creations or search_mana_creations, nor does it state when not to use this tool.
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.
Each tool targets a clearly distinct resource and action: docs vs creations vs creators vs tags, and get vs list vs search. Even the paired doc tools are unambiguous because one returns a single document while the other lists available documents.
All tool names follow a consistent verb_noun snake_case pattern using get_, list_, or search_ plus a resource name. Singular and plural forms are used correctly and predictably.
Six tools is a well-scoped set for a public read-only browsing and documentation server. Each tool covers a distinct user need without redundancy or bloat.
The server covers the core public browsing workflows: discover via tags, search creations, fetch creation details, and view creator profiles. A minor gap is the lack of a way to list or search creators directly, but agents can likely reach creators through creation links.