dependency_audit

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

The annotations already declare readOnlyHint, idempotentHint, and destructiveHint=false, so the description's 'never installs or fixes' reinforces the safety profile rather than being new information. However, it adds valuable data-egress context by stating that package versions are sent to the configured npm registry, which tells the agent that this run has network side effects and depends on registry configuration.

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 short, front-loaded sentences: the core action first, then the data-egress behavior, then the negative guarantee. No 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?

The description covers purpose, safety, and network behavior, which is good for a simple one-parameter tool. However, with no output schema and no parameter documentation, it should still indicate what the audit returns (a vulnerability report) and what projectPath defaults to.

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 input schema has 0% description coverage and one parameter (projectPath) that the description never mentions. It does not explain whether the path is optional, what the default is, or whether it must be an absolute path, so the description does not compensate for the schema gap.

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 a concrete verb and resource ('Run read-only npm audit') and makes the capability clear without the agent opening the schema. The sibling tools (dependency_inventory, dependency_outdated, package_health) are not named, so the agent must still infer that this is the vulnerability-checking one rather than the outdated-version report.

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 agent must infer when to use this tool relative to alternatives, such as dependency_outdated for version drift or package_health for a broader picture. No explicit trigger conditions or exclusions are given, so the guidance is only implied by the tool name.

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