dependency_checkCheck proposed package additions or version bumps to get a proceed/wait/review/avoid verdict with evidence before changing dependencies.
Verdict (proceed/wait/review/avoid/unknown) with evidence for adding a dependency or bumping one to a version. Call BEFORE you add a package or apply any version bump.
| Name | Required | Description | Default |
|---|---|---|---|
| items | Yes | The proposed changes to check, 1 to 25. |
Changes observed during successful MCP inspections.
v6.0.1Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint, idempotentHint and openWorldHint, so safety and side-effect profile are covered structurally. The description adds the shape of the response (the five verdict values), which is genuine value, but says nothing about latency, registry lookups, or how evidence is sourced for the open-world calls.
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 sentences, no filler, and the most actionable item (the verdict vocabulary and what it covers) is front-loaded before the call-timing instruction.
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 read-only batched check with no output schema, the description supplies the decision vocabulary and correct invocation timing, and the parameter schema carries the input contract. It could do slightly more on how multiple items are reported back, but nothing essential is missing.
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 100% and the single nested parameter set is fully documented (exact version semantics, omit-from-when-adding, ecosystem enum values). The description adds nothing beyond the schema, so the baseline 3 applies.
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 deliverable (a verdict enumerating proceed/wait/review/avoid/unknown) with evidence, and a specific scope: adding a dependency or bumping one to a version. A reader can tell it is a pre-flight decision tool, though it never names which sibling (vulnerability_scan, dependency_health, upgrade_planner) it supersedes.
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?
"Call BEFORE you add a package or apply any version bump" gives an explicit trigger condition and sequencing relative to the action being gated. It stops short of naming alternatives or stating when this check is unnecessary, so it is clear context but not full when/when-not guidance.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.