inspect_package

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

readOnlyHint=true is consistent with a dry-run/inspection operation. Beyond the annotation, the description usefully discloses what the tool reports back (shipped files, junk and secret warnings, registry check), which is meaningful because there is no output schema. It does not say whether warnings block anything or how failures surface.

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?

A single telegraphic sentence with no filler; the core concept ('publish dry run') is front-loaded and the rest enumerates concrete outputs. The fragment style is terse but every element carries information.

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 one-parameter tool with an output-less schema, the description covers the essentials of what is produced. It omits where 'dir' points, whether the registry check requires network/auth, and how warnings affect the outcome, leaving some gaps for an agent deciding how to react to results.

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 0% and the single parameter 'dir' is never mentioned or explained in the description. With low coverage the description should compensate by clarifying that 'dir' is the package directory to inspect, but it does not.

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 phrase 'Publish dry run' plus the enumerated outputs (files that would ship, junk/secret warnings, registry check) makes the operation concrete and distinguishable from a real publish. It stops short of naming publish_package as the non-dry-run counterpart, so the differentiation is implied rather than stated.

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?

Usage is only implied: 'dry run' signals it should be run before an actual publish. There is no explicit guidance on when to prefer it over publish_package, no stated prerequisites, and no note about whether it can be run at any point in the workflow.

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