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

No annotations are provided, so the description carries the full burden of behavioral disclosure. It usefully reveals that the tool queries an external service (OSV.dev) and explains why the ecosystem parameter is needed. However, it does not disclose response format, network/error behavior, or exact version-matching semantics.

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 focused sentences with no filler. The primary action is front-loaded, and the ecosystem requirement is stated directly as a necessary condition.

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 and no annotations, the description provides the essential context: the external source, the target package+version, and the disambiguation requirement. It does not cover response structure or error cases, but those are less critical for this straightforward query 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?

Only ecosystem has a schema description, so coverage is 33%. The description adds context that package_name and package_version identify a specific package+version and explains why ecosystem matters for disambiguation. It does not specify version format or exact-match requirements, leaving partial compensation for the schema gap.

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: 'Query OSV.dev for known vulnerabilities in a specific package + version.' This clearly identifies what the tool does and distinguishes it from sibling scanning tools by focusing on a single package/version lookup.

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 communicates the key prerequisite: the ecosystem must be provided to disambiguate packages with the same name. It implies use for single-package vulnerability checks, but it does not explicitly say when to prefer this tool over scan_dependencies or scan_dependency_file.

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 behavioral burden. 'Fetch' makes clear this is a read-only external lookup against NVD, but it does not disclose network dependency, missing-CVE behavior, or response format.

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?

A single front-loaded sentence with no filler; the verb, target, and source all appear in the first 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?

For a single-parameter read-only lookup, the description gives enough context to invoke it correctly. It could mention return shape or not-found behavior, but complexity is low and the tool's purpose is straightforward.

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 0%, and the description only partially compensates by identifying the parameter as a CVE ID. It adds that the lookup source is NVD, but does not specify the expected format such as CVE-YYYY-NNNN.

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?

Description uses a specific verb ('Fetch') with a clear resource ('details, severity, and references for a CVE ID') and an identified source ('NVD'). This distinguishes it from sibling tools that inspect packages or dependency files rather than looking up a specific CVE.

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 context is implied: the tool should be used when a CVE ID is already known, as opposed to scanning package/dependency files via siblings. However, the description does not explicitly state when not to use it or name alternatives.

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 full burden of behavioral disclosure. It identifies OSV.dev as the backend and indicates batch behavior, but does not described read-only semantics, network/API dependency, rate limits, or what happens when no vulnerabilities are found.

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?

A single, front-loaded sentence with no wasted words. It immediately conveys the core action, object, and target service.

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 and no annotations exist, so the description should explain more about expected results and operational behavior. It does not mention the return shape, error conditions, or how this tool relates to its siblings, leaving important context for the agent 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?

The ecosystem parameter is already documented by the schema's enum and description. The description's 'named dependencies (with versions)' adds some meaning to the dependencies array but does not explain version format or the structure of each item beyond what the schema already shows. With 50% schema coverage, the description only partially compensates.

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 ('Batch-check') and a clear resource ('a list of named dependencies (with versions) against OSV.dev'). The batch/list framing differentiates it from sibling tools like check_package or scan_dependency_file, which are likely single-package or file-based.

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?

Although the word 'batch' implies the tool is for dependency lists, there is no explicit when-to-use guidance, no mention of alternatives, and no exclusions. An agent must infer from sibling names rather than from the description.

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 full burden of behavioral disclosure. It does add useful context by stating that every listed dependency is checked against OSV.dev, but it omits details like return shape, network/API behavior, error handling, or whether transitive dependencies are included.

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 description is one tight sentence with no filler. The core action is front-loaded, and every phrase contributes either to the input format or the purpose.

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?

The description is adequate for basic invocation: it names inputs and the operation. However, with no annotations and no output schema, the agent is left guessing about the result format, failure modes, and what 'check every listed dependency' returns in practice.

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 0%, so the description must compensate. It names the allowed file types, mapping directly to the file_type enum, and explains that file_contents should be the raw manifest contents. It does not add encoding or format nuances, but it sufficiently clarifies both parameters.

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 specific verbs ('parse', 'check') and names the exact resource (package.json or requirements.txt) plus the target database (OSV.dev). It clearly conveys what the tool does, but it does not explicitly differentiate from the sibling scan_dependencies, so it stops 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 phrase 'Parse the raw contents...' implies the right use case: when an agent has raw manifest file contents rather than package names. However, it provides no explicit when-to-use/when-not-to-use guidance and does not mention any sibling alternatives.

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