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

Annotations already convey read-only, idempotent, open-world, non-destructive behavior, so the description adds meaningful operational context: it queries OSV, supports up to 50 versions, uses specific severity labels, and includes upgrade and metric data. This goes beyond what annotations alone tell the agent.

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?

One dense sentence with no filler: it front-loads the core action, then packs in the limit, ecosystems, data source, ranking output, upgrade recommendation, and supporting metrics. Every clause contributes useful 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?

The tool has one parameter, a rich output schema, and strong annotations. The description supplies the remaining operational context: input limits, supported ecosystems, severity taxonomy, upgrade behavior, and metric fields. No critical detail needed to call it 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 0%, so the description must compensate, and it does: it explains that the packages input should contain up to 50 package versions, lists possible ecosystems, and states what will be produced for each. It does not restate required fields like name, version, and ecosystem, but those are already clear in 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?

The description names a specific action and resource: it 'Checks up to 50 package versions' against OSV and 'ranks each package by its worst vulnerability' with severity categories. It also names the supported ecosystems, which clearly separates it from sibling tools like recent_exploited or vuln_details.

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 clearly implies when to use the tool: when the user supplies package versions and wants vulnerability severity, upgrade paths, and KEV/EPSS/CVSS details. It does not explicitly state when not to use it or name alternative sibling tools, so it stops short of a 5.

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 indicate read-only, idempotent, and non-destructive behavior; the description adds useful context without contradicting them. It discloses the maximum input size, the risk classification logic, and the specific data returned per row (KEV dates, ransomware use, EPSS, CVSS, SSVC).

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 compact sentences lead with the core action, then detail output categories and fields, and end with a clear takeaway. No wasted words; every sentence contributes to selecting and invoking the tool correctly.

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 a single input parameter, rich annotations, and an existing output schema, the description fully covers what an agent needs: the input format, size limits, risk ranking behavior, and the kind of information included. Nothing essential 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?

The schema already documents the single 'ids' parameter with 100% coverage万万, so the baseline is 3. The description adds beyond the schema by specifying the accepted ID formats (GHSA, PYSEC, GO, RUSTSEC) and clarifying the output categories, which helps an agent know what inputs are valid.

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 ('Ranks') and a clearly defined resource: up to 100 CVE or advisory IDs. It explicitly names the output risk categories (act_now, high, medium, low) and the decision factors, making it easy to distinguish from the sibling tools.

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 clearly implies when to use this tool: when you have a list of vulnerability IDs and need them prioritized by exploitation risk. It does not explicitly name alternatives or exclusions, but the context is clear enough for an agent to select it for ranking and prioritization tasks.

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, openWorldHint, idempotentHint, and destructiveHint false, so safety is covered. The description adds behavioral details beyond annotations: newest-first ordering, optional filters, and the specific row fields returned (CVE, vendor, product, name, date added, federal due date, EPSS). This gives the agent a clear expectation of output shape and ordering without contradicting 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 with zero waste. The first sentence front-loads the core purpose and filters; the second lists output fields. Every word contributes to the agent's understanding. This is appropriately concise.

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 the moderate complexity (4 optional parameters), existing output schema, and comprehensive annotations, the description covers the essential functional aspects: time window, filters, ordering, and output columns. No critical gaps for calling the tool correctly. Slight omissions like pagination or limit semantics are minor and covered by defaults.

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 does: 'last N days' explains the days parameter, 'optionally only for a vendor or product' explains vendor_or_product with examples, and 'only ransomware-linked' explains ransomware_only. The limit parameter is not explicitly mentioned, but the default of 25 and the context of returning rows implies it. The examples (fortinet, chrome, exchange) add practical value.

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 action (retrieve CISA KEV additions) with a clear resource (the Known Exploited Vulnerabilities catalog) and time window (last N days). It distinguishes itself from siblings like package_vulns (package-specific) and vuln_details (details) by focusing on recent additions. The mention of filters and output fields further clarifies scope.

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 clearly implies usage for recent CISA KEV entries with optional filtering. It doesn't explicitly exclude alternatives or name sibling tools, but the context makes it obvious this is for time-based catalog queries, not package or prioritization tasks. This is clear context without 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 readOnly, openWorld, idempotent, and non-destructive behavior. The description adds a notable behavioral detail: references are ordered 'patches first,' which is not inferable from annotations. It also specifies the KEV entry includes required action, due date, and ransomware status, providing output-shaping context. No contradiction with annotations, and the description adds value beyond them.

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 a single, information-dense sentence that front-loads the core purpose ('Everything about one CVE or advisory id') before listing specific data categories. Every clause adds substantive information, and there is no fluff or redundancy. It is efficient and well-structured for an agent to parse quickly.

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 the tool's complexity (many data fields), the output schema exists (as indicated), and annotations cover safety, the description is remarkably complete. It enumerates all major data types returned, including priority tier reasoning, CWE, CVSS, CISA SSVC, KEV details, EPSS, affected products/packages, and references. Nothing an agent needs to decide whether to call this tool 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?

The schema already fully documents the single 'id' parameter with 'CVE or advisory id' and length constraints (coverage 100%). The description does not elaborate on the parameter format, validation, or examples beyond what the schema provides. Baseline of 3 is appropriate since no additional semantic value is added.

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 states the tool provides 'everything about one CVE or advisory id' and enumerates specific data categories (priority tier, CWE, CVSS, EPSS, affected products, etc.). This is a precise verb+resource definition that distinguishes it from siblings like package_vulns (focused on packages) and prioritize_vulns (ranking), making the purpose unmistakable.

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 implies usage: you call this when you have a specific CVE or advisory ID and need comprehensive details. It doesn't explicitly contrast with alternatives, but the title 'One vulnerability in depth' and the single 'id' parameter make the context clear. No explicit when-not or alternative routing is given, so it falls short of a 5.

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