pkg-oracle — Dependency Trust Oracle

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

With no annotations, the description carries the full burden and does so: it discloses the verdict semantics (ALLOW/WARN/BLOCK with what each means), that BLOCK implies hallucinated names, typosquats, or critical/high CVEs, and the payment behavior (first 5 calls free, then x402 USDC on Base with a payment-required error). These are exactly the operational facts an agent needs and none of them are derivable from structured fields.

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?

It is a dense paragraph rather than a terse one, but it is front-loaded with the core purpose and every subsequent clause adds operationally useful information (checks performed, verdicts, payment). The verdict and payment sentences are long, but none is filler, so it falls just short of maximally tight.

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 tool with no annotations and no output schema, the description supplies everything needed to invoke and interpret it: the inputs' intent, the full set of internal checks, the possible return verdicts, and the error/payment behavior. Nothing an agent needs to call this correctly 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%, so the schema already documents name, version, and ecosystem in detail (including case-sensitivity for npm scoped packages and version-string format). The description mentions manifest file types but does not add syntax or format meaning beyond the schema, so the baseline of 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?

The description names a specific operation (verifying a package before it is written into a manifest) and enumerates the concrete checks performed: registry existence, OSV.dev CVE lookup, OpenSSF Scorecard via deps.dev, and a Levenshtein typosquat/slopsquat check. An agent understands exactly what this tool does without opening the schema, and it is unambiguous about the resource (a package in a given ecosystem).

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 gives explicit timing and exclusionary guidance: 'Call this BEFORE writing any package into a manifest' and 'Always call this before running an install command for a package you have not already verified in this session.' The condition for reuse (already verified in-session) is stated, so an agent knows when not to call it.

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