check_package

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

No annotations are present, so the description carries the safety and behavior burden. It discloses output form ('One line per input with its verdict and the reason') and clarifies that the tool does not perform package lookups or project audits, which is important behavioral context. It doesn't explicitly list side effects or auth needs, but the operation is a non-mutating check and the main behavioral boundaries are stated.

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 front-loaded with the purpose, then neatly organized into Args and Returns. Every sentence adds value, and the examples are compact rather than bloated.

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?

The required names parameter is fully specified and the output schema covers return values, so an agent can make a default call. The main gap is the context parameter, whose valid values are only referenced through audit_project rather than described here. This keeps the definition from being fully self-contained.

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?

Although schema coverage is 0%, the description compensates thoroughly for names with concrete accepted forms, SPDX-style expressions, and comma-separated/array variants. Context is only cross-referenced to audit_project rather than fully explained, but the schema's default and type still apply.

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 pair and timeframe ('Check ... before installing'), then sharpens the scope by stating inputs are license strings, not package lookups, and names audit_project as the installed-project alternative. This makes the tool's role unambiguous relative to its siblings.

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 explicitly states when to use the tool ('before installing them') and when not to (for actual installed-package audits, 'use audit_project'). The exclusion of project-directory lookups is direct, leaving no inference needed. generate_notices is not mentioned, but the main decision boundary is covered.

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