UK Data: CVEs and package popularity

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

Annotations already declare readOnly, idempotent, openWorld and non-destructive, so the safety profile is covered. The description adds two things annotations cannot convey: the shape of the payload (total and recent download counts, latest version) and a cost of 1 credit, which is operationally important for an agent budgeting calls. It does not mention failure behavior for misspelled or nonexistent crate names.

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, zero filler, front-loaded with purpose and followed by the return contents and cost. Every clause carries distinct 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?

No output schema exists, and the description compensates by naming the returned fields, plus it discloses the credit cost. A minor gap remains around error/empty-result behavior, but for a one-parameter read-only lookup this is close to sufficient.

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?

With a single parameter and 100% schema description coverage (including the 'e.g. "serde"' example), the schema already does the documentation work. The description implies the parameter is a Rust crate name but adds no format, casing, or normalization guidance beyond that.

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 verb and resource ('Get download statistics and metadata for a Rust crate') plus the exact source ('from crates.io'), which cleanly separates it from the npm_stats and pypi_stats siblings without needing to name them. The follow-up sentence enumerates the returned fields, so an agent knows precisely what it gets.

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 ecosystem binding ('Rust crate from crates.io') implicitly routes the agent away from npm_stats/pypi_stats and toward this tool when the package is a Rust crate. There are no explicit exclusions or pointers to complementary tools (e.g. package_info), so it falls short of a full when/when-not statement.

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?

The annotations already establish that this is a read-only, idempotent, non-destructive, open-world lookup, so the description's job is to add context beyond that. It does: it names the upstream source (NIST NVD), enumerates the return payload (description, CVSS score, severity, dates, CWE, references), and discloses a cost of 1 credit, which is operationally meaningful for an agent budgeting calls. It does not cover behavior for missing CVEs or ID format edge cases.

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 tight sentences that front-load the identity of the tool, then the return contents, then the cost. The only waste is the duplicated CVE example already present in the schema; otherwise every clause 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?

With no output schema, the description must carry the return-value burden, and it does so by enumerating every field an agent can expect, plus the data source and credit cost. For a one-parameter lookup this is nearly complete; only error/not-found behavior is unaddressed.

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% for the single cve_id parameter, and the schema already supplies the format and the CVE-2021-44228 example. The description repeats the same example without adding syntax rules, validation expectations, or normalization guidance, so the schema does the heavy lifting and 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?

The description names a specific resource (a single CVE, retrieved by its CVE ID) and a specific behavior (returning details), with a concrete example identifier. That verb-plus-resource specificity implicitly separates it from package-scanning siblings like vuln_check or package_info, but no sibling is actually named or contrasted.

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?

When-to-use is only implied: an agent can infer this is the tool for looking up one known CVE identifier. There is no explicit guidance on when to prefer it over vuln_check or other vulnerability-adjacent tools, and no statement about what happens with an unknown or malformed ID.

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?

Annotations already declare readOnlyHint, idempotentHint, openWorldHint and destructiveHint=false, so safety is covered structurally. The description adds the metric semantics (total downloads for the last week) and a cost signal ('1 credit'), which is genuine added value, but it does not say what happens on an unknown package name or whether the figure is a point-in-time snapshot versus cached data. Net effect is modest beyond the annotations.

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 plus a short cost tag, with the verb and resource front-loaded. Nothing is redundant and every sentence contributes either scope or return-value 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 single-parameter read tool with no output schema, the description is nearly sufficient: it names the registry, the metric, and the time window of the result. The only shortfall is that 'statistics' in the name implies a richer payload while the text promises only a weekly total, a mild ambiguity an agent may notice.

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?

With one parameter at 100% schema description coverage (including the 'react' example), the schema already carries the semantics. The description reinforces the scope by stating the input must be an npm package on that registry, which is a small but real clarification of accepted values beyond the generic 'npm package name' field text.

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 verb ('Get download statistics') and a precisely scoped resource ('a JavaScript package on the npm registry'). That registry qualifier implicitly separates it from the sibling pypi_stats and crate_stats tools, so the agent can pick the right one without opening a 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?

Usage is only implied via the stated goal ('gauge popularity and usage trends'). There is no explicit when-to-use guidance, no exclusion of alternatives such as package_info, and no statement about what to do if the package does not exist. Adequate but with a clear routing gap.

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?

Annotations already declare readOnly, idempotent, non-destructive and open-world, so the safety profile is covered. The description still adds real context beyond them: the response granularity (last day, week, month) and the 1-credit cost, both of which affect invocation decisions.

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, front-loaded with purpose and followed by return content and cost. No filler or restated title.

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 single-parameter read tool with no output schema, the description tells the agent what data orientation comes back (day/week/month counts) and the credit cost. Only the response field names and error behavior are unspecified, which is minor here.

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?

With one parameter at 100% schema description coverage, the schema already documents the package name and gives a "requests" example. The description adds no syntax, naming, or case-handling detail beyond that, so 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?

"Get download statistics for a Python package from PyPI" states a specific verb and resource, and naming PyPI implicitly separates it from npm_stats and crate_stats. It stops short of explicitly routing the agent away from those package-ecosystem siblings.

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 phrase "to measure library adoption" hints at the use case, but there is no explicit when-to-use/when-not guidance and no named alternative for other registries or for non-download package metadata (package_info).

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