Read the full entrypoint and manifest for one public text Skill selected by exact canonical identity and optional revision. After completing the task, optionally call skills_feedback with the Skill name, a 1-5 rating, and a concise issue when useful.
| Name | Required | Description | Default |
|---|---|---|---|
| name | Yes | ||
| parts | No | ||
| paths | No | ||
| traversal | No | ||
| artifactRevision | No | ||
| artifactVersionId | No |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The readOnlyHint annotation already signals a safe read, and the description adds useful context about public text Skills and canonical identity. But it does not disclose behavior for missing skills, return format details, or limitations, so it adds only modest value beyond the annotation.
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, front-loaded with the tool's action and scope, and the second sentence provides actionable follow-up guidance. Every sentence earns its place with no redundancy.
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?
Despite the readOnlyHint annotation, the tool has six parameters, nested objects, and no output schema, and the description does not explain key parameters like parts, paths, or traversal. It is adequate for a simple read but notably under-specified for correct invocation of all available options.
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 carries the burden for explaining the six parameters, but it only clarifies 'name' as canonical identity and 'optional revision' (likely artifactRevision). It leaves parts, paths, traversal, and artifactVersionId unexplained, which is a significant gap given the nested schema.
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 ('Read') and resource ('full entrypoint and manifest for one public text Skill'), and clarifies that selection is by 'exact canonical identity' with 'optional revision.' It does not explicitly contrast this with sibling tools like skills_feedback or capabilities_search, so sibling differentiation is mostly implicit.
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 implies usage when you need to read a known Skill by canonical identity, and it provides concrete follow-up guidance to optionally call skills_feedback. However, it does not explicitly state when to use this tool instead of alternatives, nor does it mention exclusions or prerequisites beyond exact identity.
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 owns a distinct resource/action pair (e.g., search/get/preflight/execute for capabilities, read/feedback for skills, status/connect/disconnect for vault), and detailed descriptions make boundaries explicit. No two tools appear to do the same thing, and the preflight/execute separation is clearly delineated.
Naming mixes bare nouns (auth, billing, vault), prefixed subject-verb pairs (capabilities_execute, skills_feedback), and the outlier 'loadout_bug_submit' with inconsistent pluralization (capabilities vs skills vs loadout). Although all tokens are lowercase and underscore-separated, there is no single predictable pattern, and some tools (e.g., 'billing') are action containers while others are single-action functions.
Thirteen tools is well within the ideal 3–15 range, and each tool serves a clearly separable domain (authentication, billing, capabilities, skills, vault, audit, feedback, bug reporting). No tool feels redundant, and the count is appropriate for the breadth of functionality offered.
The surface covers the full lifecycle for capabilities (search/get/preflight/execute/feedback) and handles account, billing, vault, audit, and support needs. The only gap is lack of a general skill search or listing capability—skills can only be read by exact canonical identity, which may impede discovery—but core workflows are otherwise complete.
