Abandonment checks for WordPress, npm and PyPI packages, priced per call.
Scored across 2 tools
package_check performs the core abandonment assessment while package_sources exposes registry endpoints and scoring rules. The two tools have clearly distinct purposes with no overlap, so an agent can easily select the right one.
Both tools follow the same consistent snake_case package_<noun> pattern (package_check, package_sources). The convention is predictable and readable.
With only two tools, the surface is on the thin side even for a narrow micro-service. The set is focused and each tool earns its place, but it sits at the borderline of minimal scope.
The core lifecycle (assess a package, inspect sources/scoring rules) is covered for the stated purpose. Minor gaps exist, such as no batch checking of multiple packages at once, but agents can work around this with repeated calls.
Check whether a WordPress.org plugin, npm package or PyPI project is abandoned. Costs $0.02 per call via x402. Returns status (active, stale, abandoned, deprecated or closed), a 0-100 abandonment-risk score, months since the last update, the latest release, and the signals behind the score. Signals, not a verdict: check the project before deciding.
| Name | Required | Description | Default |
|---|---|---|---|
| name | Yes | npm package ("express", "@scope/pkg"), PyPI project ("requests"), or WordPress.org plugin slug ("contact-form-7"). | |
| ecosystem | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With readOnlyHint=true already declaring the safety profile, the description adds genuinely new behavioral context: a per-call cost of $0.02 via x402, and an enumeration of the returned fields (status values, risk score, months since update, latest release, signals). This is far more than the annotation conveys, though it doesn't discuss rate limits or failure modes.
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 tight sentences, front-loaded with the core purpose and followed by cost, then return shape, then interpretive caveat. Every sentence carries information, though the return-field enumeration is slightly list-like.
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?
Since there is no output schema, spelling out the status vocabulary, risk score range, and signal fields is exactly what the description should do. The only gap is the absence of any routing cue relative to the sibling package_sources.
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 only 50%: the 'name' property is documented with concrete examples, but the 'ecosystem' enum has no description. The description partially compensates by naming the three ecosystems (WordPress.org, npm, PyPI), which maps to the enum values, but it adds no format guidance beyond what the name description already provides.
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?
States a specific verb ('Check') and resource ('whether a WordPress.org plugin, npm package or PyPI project is abandoned'), naming all three ecosystems the tool covers. An agent can immediately tell this apart from package_sources, which implies source retrieval rather than abandonment assessment.
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 closing line, 'Signals, not a verdict: check the project before deciding,' gives useful interpretation guidance. However, it offers no explicit when-to-use vs. the sibling package_sources, nor any statement of when this tool is unnecessary, so usage is only implied.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
List the registry endpoints this service reads, the scoring rules and the cache policy. Free.
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
readOnlyHint already declares this is a safe read, so the bar is lower. The description adds cost context ('Free') not present in annotations, but says nothing about output format, pagination, or freshness of the cache policy it reports.
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 short sentences that front-load the content categories, with the cost note trailing. The 'Free.' fragment is terse but earns its place; nothing is padded.
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 zero-parameter, read-only informational tool with no output schema, the description adequately names what the agent will learn. It is thin on the shape of the returned data but the tool's scope is inherently simple.
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?
The tool takes zero parameters, so per the calibration baseline a 4 applies. There is no parameter surface for the description to compensate for.
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?
States a specific verb (List) and enumerates the three resource categories returned: registry endpoints, scoring rules, and cache policy. It is clearly an informational/read tool, distinguishable in spirit from package_check, though the sibling is never named.
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 only usage signal is the word 'Free,' which hints at cost but does not say when to call this versus package_check or under what circumstances an agent should inspect the service's sources and scoring rules.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
package_checkpackage_sourcesPackage intelligence for AI agents across npm, PyPI, crates.io and deps.dev. No API keys.
Package intelligence for AI agents across npm, PyPI, crates.io and deps.dev. No API keys.
Pay-per-call DNS/TLS truth and npm/PyPI breakage checks via x402. No account or API key.
check-package: block malicious npm/PyPI deps before your AI agent installs them. Free, no key.