package_trust_check

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

There are no annotations, so the description carries the behavioral burden. It adds useful operational details: the $0.05 USDC cost and the catalog fallback caused by the API being unreachable at startup. Still, it doesn't state that the operation is read-only, how fresh the underlying data is, or how the trust score is calculated.

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 core purpose is front-loaded in a single sentence, followed by a concise list of outputs)Skip the score steps through the dialect so that it reads quickly. The operational parentheticals add relevant context without bloating the description.

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?

There is no output schema, so the description must explain return value shape. It lists the major output categories and the 0-100 trust score, which is enough to invoke the tool. It doesn't cover response format, unknown-package handling, or data-freshness limitations, leaving some post-call ambiguity.

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 schema already covers 'name' and provides an npm/pypi enum. The description repeats the ecosystem options but doesn't add meaningful parameter details beyond the schema. With two simple parameters and 50% schema coverage, this is adequate but not additive.

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?

Clearly specifies a concrete purpose: evaluating install-safety for npm or PyPI packages. Enumerates the signal categories and trust score, so an agent immediately knows what the tool does and how it differs from list_products and repo_merge_lookup.

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 'install-safety signals' framing implies this is meant for vetting a package before installation, and the ecosystem field narrows input. However, there is no explicit when-to-use vs alternatives language or conditions that would trigger choosing this tool over its siblings.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.