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

Annotations already declare readOnly/idempotent/non-destructive, and the description adds genuinely new behavioral facts: results come from deps.dev, the scope is direct (not transitive) dependencies, and version defaults to latest. It omits rate limits and result shape, but the output schema covers the latter.

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 sentences, front-loaded with the core action before the rationale and supported ecosystems. Slightly redundant in re-listing 'npm, pypi, cargo' when the schema already enumerates them.

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 read-only lookup with rich annotations, full schema coverage, and an output schema, the description supplies everything needed to select and invoke it correctly: source, scope, default behavior, and supported ecosystems.

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%, with clear per-parameter descriptions and an enum for ecosystem, so the baseline is 3. The description only restates the version default and lists the ecosystems, adding nothing the schema does not already provide.

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?

Specific verb (List) plus precise resource and scope: direct dependencies of a specific package version, sourced from deps.dev. The 'direct' qualifier separates it in spirit from a transitive-dependency or package_info sibling, though no sibling is named explicitly.

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?

Gives a concrete use context – understanding what a package pulls in before adding it – which tells the agent when this tool is relevant. It stops short of naming alternatives (package_info, package_health) or stating when not to use it.

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, open-world and non-destructive, so the safety profile is covered. The description adds only the notion of 'recent' download counts, without specifying the time window, data source, or rate limits — modest added value beyond structured data.

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 with no filler; the purpose comes first and the ecosystem scope is confined to a single closing clause.

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 an output schema present, return-value documentation is not required, and the description covers purpose, scope and the ecosystem boundary. It is slightly thin on the 'recent' semantics, which matters for interpreting the returned numbers.

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 both parameters are documented in the schema with examples and an enum, so the description need not compensate. It confirms the three supported ecosystems but adds no naming or format guidance beyond the schema.

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: retrieve popularity/download statistics for a package, with the qualifier 'recent download counts'. It implies separation from package_info/package_versions/package_health but never names or contrasts with any sibling, so differentiation is left to inference.

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?

'Useful for judging how widely used and battle-tested a dependency is' gives a clear decision context for choosing this tool, and the ecosystems list scopes it. It stops short of saying when to prefer it over package_health or package_info, or any exclusions.

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, destructiveHint=false and openWorldHint, so safety is covered. The description adds real behavioral context beyond that: the specific signals aggregated, the upstream data source (deps.dev), and that the result is an actionable summary. It stops short of noting latency/cost of a multi-source composite call.

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, front-loaded with the purpose and the checklist of signals. The closing 'Returns a summary an agent can act on' is slightly filler and contributes little given an output schema exists.

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?

Given an output schema exists, the description need not explain return values, and it covers scope, signals checked, source, and supported ecosystems. Only minor operational details (composite-call latency, no auth/rate-limit notes) are absent, which is low-stakes for a read-only public lookup.

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% with only two parameters, and the schema already documents both the exact-name convention and the ecosystem enum. The description's ecosystem list ('npm, pypi, cargo') merely repeats the enum, adding no new meaning. 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?

Names a specific resource (package) and verb-like scope (composite trust/health check), then enumerates exactly what is checked: recency, deprecation, license, maintainers, dependency count, advisories. The 'composite' framing and the six-signal list distinguish it from the single-facet siblings such as package_dependencies and package_info.

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?

'A composite trust/health check for a package an agent is considering' gives a clear context for use (pre-adoption vetting). It does not, however, name any sibling alternative or state when a narrower tool like package_info or package_dependencies should be preferred instead.

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, open-world behavior, so the safety profile is fully covered. The description adds the deprecation flag and the cross-registry scope, but the field list largely duplicates what the output schema would document. With rich annotations and an output schema, the incremental behavioral disclosure is modest.

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 tightly written sentences: the payload is front-loaded, the ecology scope closes it out, and there is no redundant or filler text. Every clause carries information an agent needs to call the tool.

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 two-parameter read-only lookup with full schema coverage, rich annotations, and an output schema, this is essentially complete; the description needn't explain return values. The only omission is guidance pointing to sibling tools when the agent needs health, downloads, or dependency data instead.

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 both parameters are already documented, and the enum constrains ecosystem. The description only restates the ecosystem list ('npm, pypi, cargo') and adds no format guidance for 'name' (e.g., scoped packages, case sensitivity). Baseline 3 applies when the schema does the heavy lifting.

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 core metadata for a package') and enumerates the exact fields returned (version, description, license, homepage, repo, maintainers, deprecated flag), which implicitly separates it from siblings like package_downloads or package_dependencies. However, no sibling is named explicitly, so the agent must infer the boundary against package_health and package_versions.

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?

'Use before an agent installs or recommends a dependency' gives a clear, actionable trigger condition for when this tool applies. There are no exclusions or named alternatives (e.g., when to prefer package_health or package_versions), so the routing guidance stops short of the explicit when-not framing.

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, destructiveHint=false and openWorldHint, so the safety profile is covered without the description. The description adds the ecosystem support boundary, but says nothing about result ranking, rate limits, or network/auth behavior expectations of a search call.

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 capability statement is front-loaded before the ecosystem constraint. Every clause carries information an agent needs.

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?

An output schema exists, so return values need not be described, and the ecosystem limitation is disclosed. What remains thin is guidance on how keyword matching behaves or what to do when a search returns nothing, which is minor for a read-only search tool.

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 coverage is 100%, so the baseline is 3. The description earns an extra point because the ecosystem sentence resolves a genuine inconsistency in the schema, whose enum lists only npm/cargo while its own property description claims "One of: npm, pypi, cargo." That clarification is real value beyond the structured fields.

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 ("Search for packages by keyword") and describes the result shape ("top matches with descriptions"), which cleanly separates it from siblings like package_info or package_versions. It does not explicitly name a sibling to differentiate against, so it falls short of a 5.

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 note gives real selection guidance: the tool only works for npm and cargo, and PyPI is excluded because it has no public search API. That is an implicit when-not condition, though no alternative tool is named for the cases this one cannot serve.

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, and destructiveHint=false, so the safety profile is covered by structured data. The description adds useful behavioral context (result ordering, maintenance-check framing, supported ecosystems) but says nothing about pagination, truncation at the limit, or behavior for unknown packages.

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 sentences, front-loaded with the core action and scope, then usage rationale, then ecosystems. The ecosystem list is mildly redundant with the schema enum, but there is no padding or 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?

With an output schema present, the description need not explain return values, and it correctly focuses on scope, ordering, and the maintenance-check use case. The only gap is the absence of any tie-breaker guidance against the five sibling package tools.

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 all three parameters, including the enum values and the limit default. The description repeats the ecosystem list and does not add format or syntax detail beyond the schema, making the baseline 3 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 states a specific verb and resource ('List recent released versions of a package'), adds the sort order ('most recent first'), and names the result fields (release dates). It is clearly distinct from package_downloads or package_dependencies, though it does not explicitly contrast itself with sibling tools like package_info.

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 offers implied usage ('pick a version or check how actively it is maintained'), which tells the agent the intent behind the call. However, there is no explicit when-to-use vs when-not guidance and no mention of alternatives such as package_info or package_health, so the agent must infer the boundary.

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