Sharebench — search & pull AI skills, agents, prompts & playbooks (SKILL.md) into any MCP client
Scored across 2 tools
search is for finding artifacts and returns metadata, while get_by_id retrieves the full content of a single artifact. Their purposes are fully distinct with no overlap, and the descriptions explicitly reference each other to form a clear two-step flow.
Both tools use snake_case and are readable, but one is a bare verb ('search') while the other follows a verb_preposition_noun pattern ('get_by_id'). This is a minor inconsistency but not confusing.
With only two tools, the server feels quite thin. The read-only search-and-fetch scope justifies a small set, but it is on the borderline of being too minimal for a tool server.
The server only supports searching and fetching artifacts. There are no tools for creating, updating, deleting, or contributing artifacts, despite the descriptions hinting at 'contributing' as a use case. This is a significant functional gap.
Fetch the full SKILL.md content and metadata for a single artifact. Provide EXACTLY ONE of artifactId (the UUID returned by search) or slug (the URL-safe identifier, e.g. from a /p/<slug> link). Passing both or neither returns a validation_failed error. Use this after search to retrieve the body of a hit the user wants to read, summarize, apply, or fork. Returns the artifact's name, description, type, contributor, version, timestamps, the full SKILL.md text (YAML frontmatter + markdown body, up to 256 KB), the number of bundled extras (bundledCount), their filenames (bundledFilenames), per-file metadata in bundledFiles (each entry has key, filename, and originalRef — the EXACT body-relative reference string the importer matched, or null when the file was bundled without a body reference; use this to translate a link span in the body back to its bundle filename), and the public-surface fields slug, authorCredit, industries. To fetch a bundled extra, read it as a resource at artifact://<artifactId>/bundled/<filename>.
| Name | Required | Description | Default |
|---|---|---|---|
| slug | No | URL slug for the artifact (e.g. `brand-voice`). Take this from the `slug` field of a `search` result or a /p/<slug> link. Mutually exclusive with `artifactId`. | |
| artifactId | No | UUID of the artifact. Take this from the `artifactId` field of a `search` result. Mutually exclusive with `slug`. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries full burden and fully delivers: it discloses the validation error behavior, the 256 KB size cap, the structure of bundled extras (`bundledCount`, `bundledFilenames`, `bundledFiles`, including `originalRef` semantics), and how to fetch a bundled extra via `artifact://` URI. This exceeds minimal expectations.
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 long but information-dense and well-structured: it starts with a clear thesis, then details usage, constraints, return fields, and bundle handling. Every sentence carries technical value, though some could be tightened without loss.
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?
Given the tool's complexity, the absence of an output schema, and two optional but mutually exclusive parameters, the description is remarkably complete. It covers input validation, output shape, size limits, bundle metadata semantics, and follow-up resource URIs, leaving little ambiguity for an agent.
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 coverage is 100% and both parameters already have detailed descriptions with mutual-exclusivity. The description adds practical sourcing context (take `artifactId`/`slug` from a `search` result or `/p/<slug>` link) and clarifies the exact error condition, going beyond the schema baseline.
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 opens with a specific verb+resource: "Fetch the full SKILL.md content and metadata for a single artifact." It clearly distinguishes itself from the sibling `search` tool by focusing on retrieving one artifact's full content after search.
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?
Provides explicit usage guidance: exactly one of `artifactId` or `slug` must be provided, both/neither causes a `validation_failed` error, and states to use it after `search` to retrieve content the user wants to read, summarize, apply, or fork. This is strong when-to-use and what-not-to-do guidance.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Search this workspace's published artifacts (skills, agents, workflows, and knowledge documents in SKILL.md format). Returns ranked metadata — name, description, type, contributor, timestamps, bundledCount, slug, authorCredit, and industries — but NOT the full body. To read an artifact's content, call get_by_id with the returned artifactId (or slug), or read it as a resource at artifact://<artifactId>. Use this whenever the user wants to find, discover, browse, or filter existing artifacts before reading or contributing. Modes: hybrid (default; combines lexical and semantic ranking via reciprocal rank fusion — best for most queries), bm25 (exact-keyword or name lookups), semantic (concept matching when the user's terms differ from artifact text). Pass industries: ['marketing', 'legal'] to narrow results to artifacts tagged with ANY of those industries (keyword-array overlap). If hybrid silently degrades because the embedding service is unavailable, the response's warnings array will contain embedding_degraded:hybrid-fell-back-to-bm25 — surface this to the user if precision matters.
| Name | Required | Description | Default |
|---|---|---|---|
| mode | No | Ranking strategy. Default: hybrid. | |
| type | No | Filter by artifact category. Omit for all types. | |
| limit | No | Maximum hits to return. Default: 20. | |
| query | Yes | Free-text query. Names, phrases, or natural-language concepts. | |
| offset | No | Pagination offset for navigating result sets. | |
| industries | No | Filter to artifacts tagged with ANY of these industry slugs (keyword-array overlap). Up to 5 values. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description fully discloses behavior: it returns only metadata (not full body), explains ranking modes and their trade-offs, and reveals the silent degradation scenario with the exact warning string and instructions to surface it. This goes well beyond a typical read-only tool description.
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 denser than the ideal two-sentence example but every sentence contributes: scope, return fields, usage, mode choices, and a warning fallback. It is front-loaded with the core purpose and well-structured, though slightly long; the detail is justified by the tool's complexity.
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 6-parameter tool with no output schema, the description covers return value composition, field list, exclusions (full body), navigation to `get_by_id`, mode semantics, industry filtering, and a fallback warning. No critical gaps remain for an agent to use the tool effectively.
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 coverage is 100%, so baseline is 3. The description adds meaningful context for `mode` (explaining hybrid via reciprocal rank fusion, bm25 for exact matches, semantic for concept matching) and clarifies `industries` as 'keyword-array overlap' with ANY semantics. This exceeds schema-only information.
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 ('Search') and clearly defines the resource scope ('this workspace's published artifacts') while enumerating artifact types. It distinguishes itself from the sibling tool by explicitly stating it returns metadata only, not the full body, and directs users to `get_by_id` for content access.
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?
Provides explicit usage context: 'Use this whenever the user wants to find, discover, browse, or filter existing artifacts before reading or contributing.' It also names the alternative (`get_by_id`) and gives mode-selection guidance (hybrid for most, bm25 for exact lookup, semantic for conceptual matching).
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Search & install 6,500+ AI agent skills from skills-hub.ai inside any MCP tool.
Governed AI agent skills — one library, distributed to devs and exposed to remote agents over MCP.
A registry of 5,900+ peer-authored skills any MCP agent can search and load on demand.
One place to build, share, and govern the skills and tools your AI agents use at work.
Add one secure layer between your agents and this server.
