AIS CVE Priorities — daily exploit-ranked patch list for AI agents

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

No annotations are provided, so the description must convey behavior. It indicates a read-only, non-destructive operation (a 'teaser' that returns information), and does not imply any side effects. While it does not explicitly state 'read-only', the nature of the tool and its purpose make it clear.

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 extremely concise (two sentences) and directly states the purpose, ranking criteria, and alternative tool. No redundant information or fluff.

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?

Despite lacking an output schema, the description sufficiently indicates the return content (top-3 CVEs, no scores) and points to a sibling tool for details. It is complete for the tool's limited scope, though a more explicit mention of the return format would raise it to 5.

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 tool has zero parameters, and the schema is fully covered (empty properties). There is nothing for the description to add; no ambiguity exists regarding input semantics.

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's function: it returns today's top-3 CVE priorities based on a specific ranking (KEV + EPSS + KEV-recency) and explicitly distinguishes itself from the sibling tool 'top_cves_today' which provides the full scored list.

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 explicitly tells when not to use this tool ('Use top_cves_today for the full scored list') and explains the ranking rationale, guiding the agent to select the appropriate tool based on whether scores are needed.

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?

No annotations are provided, so the description carries the burden. It discloses the paid nature and the $0.005 cost, which is important behavioral context. It also states the verdict is from 'today's AIS ranked set,' implying recency. However, it doesn't describe what happens if the CVE is not in the set, or the format of the verdict.

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, compact sentence that front-loads the most critical information (paid access) and then states the function. Every word earns its place; no fluff.

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 one-parameter tool, the description covers the essential context: what it does and that it costs money. However, it doesn't explain what a 'priority verdict' looks like, what happens if the CVE isn't in today's set, or how the payment is processed. Given the lack of output schema and annotations, a bit more detail would help.

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 the cve_id parameter. The description adds the format 'CVE-YYYY-NNNN' implicitly via the schema, but doesn't add extra meaning beyond that. 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 clearly states the tool's function: it returns a priority verdict for a single CVE from today's AIS ranked set. The verb 'unlock' and the resource 'one CVE's priority verdict' are specific. It doesn't explicitly differentiate from siblings like top_cves_today, but the single-CVE scope is implied.

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: provide a CVE ID to get its verdict. It mentions the paid nature and payment methods, which is a prerequisite. However, it doesn't explicitly state when to use this tool versus siblings like top_cves_today or kev_fresh, nor does it mention 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?

With no annotations, the description carries the behavioral burden and does disclose an important access constraint: the tool is paid and requires an AIS Gateway key or x402 payment. However, it does not disclose return format, failure behavior, or rate limits, so coverage is partial.

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 dense sentence front-loads the payment requirement before stating the data scope. Every clause contributes useful information with no waste.

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 zero-parameter list tool, it clearly states source, freshness window, completeness, and included ranks. The main gap is that 'AIS ranks' is undefined and no output schema describes the return shape, but this is minor given the tool's simplicity.

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?

There are zero parameters and the schema is empty with 100% coverage, so the description has no parameter burden. The baseline of 4 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 identifies a specific resource: CVEs newly added to CISA KEV in the last 7 days, described as a complete catalog with AIS ranks. It lacks an explicit verb like 'returns', but the scope is unambiguous and distinct from sibling tools such as top_cves_today.

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?

There is no explicit guidance on when to use this tool instead of siblings like cve_verdict or top_cves_today. The 'complete catalog' and 7-day window hint at relevance, but the agent must infer when this tool is preferred.

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 disclosure burden, and it does so meaningfully by stating the tool is PAID and must be unlocked via an AIS Gateway key or x402 payment. It also discloses the output composition (ranked list with scores, KEV, EPSS, patch status, methodology), making the behavior reasonably predictable. It does not mention rate limits or error conditions when the payment requirement is not met, but for a zero-parameter read-only list tool this is adequate.

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 most critical operational constraint (PAID) before describing the output content. It contains no filler or redundant phrasing; every clause adds 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?

Given zero input parameters and no output schema, the description covers the essential invocation context: payment prerequisite and the nature of the returned list. It is complete enough for an agent to call the tool after ensuring the payment/key requirement is met, though it could briefly note how to supply the key if that is not handled outside the tool description.

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 tool has zero parameters, so there is no parameter meaning for the description to add; the baseline of 4 applies. The description correctly avoids inventing parameters and simply describes the returned data.

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—'Today's FULL ranked CVE priority list'—and enumerates the data it includes (scores, KEV, EPSS, patch status, methodology). It implies a list/retrieval operation even without an explicit verb like 'list' or 'get'. The word 'FULL' hints at contrast with siblings like brief_teaser, but it does not explicitly name or differentiate from the alternatives.

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 conveys that this is for a full, ranked daily CVE list, which implies when to use it, but it offers no explicit guidance about when not to use it or which sibling tools might be better suited. No alternatives are mentioned; the only usage instruction is the payment requirement. This is enough for an implied use case but lacks clear routing among the sibling tools.

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