Get core metadata for a package: latest version, description, license, homepage, source repository, maintainers, and whether it is deprecated. Use before an agent installs or recommends a dependency. Ecosystems: npm, pypi, cargo.
| Name | Required | Description | Default |
|---|---|---|---|
| name | Yes | Package/crate name | |
| ecosystem | Yes | Package registry to look in. One of: npm, pypi, cargo. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the full burden for disclosing behavioral traits. It never states whether this is a read-only operation, what happens if a package does not exist, or any error/rate-limit behavior. While 'Get' implies read-only, it is not explicit, and side-effect or failure semantics are absent.
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, no filler. The first sentence front-loads the tool's purpose and the exact metadata fields, the second specifies the usage context and supported ecosystems. Everything earns 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 2-parameter read tool with no output schema, the description is largely complete: it lists the return fields and the intended use case. It omits error behavior or edge cases (e.g., not-found handling), but given the simplicity, this is a minor gap.
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% (both 'name' and 'ecosystem' have descriptions in the schema), so the schema already documents the parameters fully. The description adds no extra meaning about parameters beyond repeating the ecosystem options, so baseline 3 is appropriate.
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 and resource: 'Get core metadata for a package' and enumerates the exact fields returned (latest version, description, license, homepage, source repository, maintainers, deprecated status). This precisely distinguishes it from siblings like package_dependencies, package_downloads, and package_health, which cover other aspects.
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?
It provides a clear when-to-use directive: 'Use before an agent installs or recommends a dependency.' This gives the agent a concrete trigger for invoking the tool. However, it does not explicitly mention when not to use it or name alternative siblings for different needs, leaving some inference to the agent.
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 distinct aspect of package intelligence: dependencies, download statistics, health, metadata, search, and version history. There is no overlap in purpose, and the descriptions clearly differentiate what each tool returns.
All tools follow the consistent pattern 'package_' plus a descriptive noun (dependencies, downloads, health, info, search, versions). The naming is uniform, snake_case, and immediately conveys each tool's function.
Six tools is well within the ideal 3–15 range and matches the server's single focus on package evaluation. Each tool covers a necessary facet without redundancy or bloat.
The tool surface covers the full lifecycle of package evaluation: discovering packages via search, inspecting metadata, checking version history, assessing popularity, and performing a composite health check including security advisories. No obvious gaps exist for the stated purpose.