get_downloadsDownload statistics for a package. Only npm (via api.npmjs.org) and PyPI (via pypistats.org) support this; any other registry returns 400 not_supported. npm returns a period window with downloads, start, and end; PyPI returns last_day, last_week, and last_month totals.
| Name | Required | Description | Default |
|---|---|---|---|
| name | Yes | Package name. | |
| registry | Yes | Target registry. Only npm and pypi expose download stats. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations provide readOnly/idempotent/destructive hints, but do not cover error behavior or return shapes. The description adds concrete details: exact API endpoints, the 400 error for unsupported registries, and the distinct response formats for npm vs PyPI.
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?
Three sentences, front-loaded with the core action, then constraints and return formats. Every sentence provides essential information without redundancy or 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?
With only two simple parameters and no output schema, the description fully covers supported registries, error handling, and return shape variations. It provides all necessary operational context for an agent to select and call the tool correctly.
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 covers both parameters with 100% coverage, so baseline is 3. The description adds value by explaining how the registry parameter affects the response structure (period window vs last_day/week/month totals), which goes beyond the schema's simple type/enum descriptions.
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 'Download statistics for a package' – a clear verb+resource with scope. It further distinguishes from siblings by detailing registry-specific behavior and supported APIs.
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 explicitly states that only npm and PyPI are supported, and that any other registry returns 400 not_supported, which sets clear usage boundaries. It does not explicitly name alternative tools, but the stated purpose differentiates it from sibling package tools.
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 have clear, distinct purposes, but get_package and get_ecosystems_package both return package metadata and could be confused; search_ecosystems and search_packages also share a similar naming pattern though their behavior differs (exact cross-registry lookup vs fuzzy within a registry). Overall, descriptions help disambiguate.
All tools follow a consistent verb_noun pattern: get_ for fetching specific data, search_ for searching. No mixed conventions or vague verbs, making the API predictable.
10 tools is well-scoped for a package/dependency intelligence server. Each tool covers a distinct aspect (metadata, versions, dependencies, downloads, vulnerabilities, insights, search) without feeling bloated or thin.
The tool surface covers core package lookups, version listing, dependency graphs, download stats, vulnerabilities (single and batch), and security insights. Minor gaps exist, such as no direct tool for comparing packages or listing maintainer info, but these are not essential for the stated purpose.