databutler-provenance

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

With no annotations, the description bears the full behavioral burden and largely succeeds: it discloses that this is a live RDAP lookup, that registrant info may be redacted, that a typosquat check is included, and that results should be treated as signals. It doesn't mention failure modes or rate limits, but the core behavioral traits and interpretive caution are well covered.

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 with no filler: the first packs a comprehensive feature list, and the second delivers the decision-relevant warning about interpreting results. The most important phrase, 'live RDAP lookup', is front-loaded.

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 lookup with no output schema and no annotations, the description is complete: it enumerates the main return categories, explains the typosquat dimension, and adds the necessary interpretative caveat. An agent has enough to invoke the tool correctly and act on the result.

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 schema already documents the single parameter with a concrete example (e.g. example.com), giving 100% schema description coverage, so the baseline of 3 applies. The description adds domain-specific context but no additional syntactic or formatting requirements beyond what the schema provides.

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 clearly identifies the tool's purpose with a specific verb and resource: a live RDAP lookup for a domain, listing registration date/age, registrar, nameservers, status, and redaction state, plus a typosquat check. It is unmistakably domain-focused and therefore distinguishable from the sibling package_provenance tool.

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 description gives clear usage context by framing the tool around phishing investigation: a recently registered domain resembling a bank or big brand is a classic signal. It also instructs the agent to report it as a signal, not a conclusion. It stops short of explicitly naming alternatives or exclusion conditions, but the intended scenario is clear.

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

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

With no annotations, the description carries the transparency burden. It discloses that the tool performs a live lookup against npm or PyPI and enumerates the returned data (publish date, release count, latest version, maintainers, linked repo, typosquat check). It does not explicitly note potential network errors or rate limits, but the 'live lookup' phrasing conveys the key behavioral trait.

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 entire description is two sentences with no filler. The opening question and colon introduce the purpose, the list of returned data is compact, and the final sentence gives a concrete usage trigger. Every part contributes meaning.

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 simple lookup tool with no output schema, the description lists the key fields returned and the intended use case, which is enough for an agent to decide when to call it. It does not explain error cases or how to interpret the typosquat result, but those are secondary for tool selection and initial invocation.

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 covers both parameters 100%, including an enum for ecosystem and examples for name. The description adds context about why the package name matters (unfamiliar dependency) but no additional semantic detail beyond what the schema already provides. Baseline 3 is appropriate.

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 uses a specific verb and resource: a live npm/PyPI lookup for package provenance and typosquat detection. It clearly distinguishes itself from the sibling domain_provenance by stating 'package' and listing package-specific data. An agent can tell this tool apart from its sibling without inspecting the schema.

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 an explicit trigger: 'Use when an agent is about to install or recommend an unfamiliar dependency.' This clearly states when to use the tool, though it does not mention when not to use it or explicitly name the alternative domain_provenence. The package-vs-domain distinction is implied by context but not stated.

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