cve-intelligence

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

With no annotations, the description carries full burden. It adds valuable context: absence semantics ('a null field means this dataset holds no such record'), field meaning ('fixed = first patched build; affected_through = last VULNERABLE build'), and auth behavior. It does not cover rate limits or errors, but covers key nuances.

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 dense and front-loaded with the core purpose. Each sentence earns its place: content enumeration, auth note, and absence semantics. It is longer than the minimal but information-dense, so it's well-structured.

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 lists the main components of the returned intelligence record and explains critical data semantics, especially for fixed/affected_through and null handling. Since there is no output schema, this level of detail is important and largely sufficient, though it omits fields like error handling or pagination (which are less relevant for a single-record fetch).

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 input schema already has 100% coverage for the single parameter 'id' with an example. The description adds little beyond what the schema provides—it reiterates that the tool is for one CVE but doesn't provide additional format details. 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 purpose: 'Full intelligence record for one CVE' – a specific verb + resource. It enumerates the content areas (CVSS, EPSS, KEV, remote-detection, Sigma, etc.), which distinguishes it from siblings like search_cves (search vs. specific fetch) and get_updates.

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 when to use this tool: when you need a full record for a specific CVE. It provides authentication guidance ('No key required over MCP...') and clarifies the semantics of fixed/affected_through. It does not explicitly exclude alternatives, but the context is clear enough for tool selection.

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 must disclose behavioral traits. It adds value by detailing the report's license (CC BY 4.0) and the citation requirement, which are behavioral expectations. However, it does not explicitly state that the operation is read-only or safe, nor does it describe any side effects or prerequisites. For a 'get' tool, the read-only nature is implied but not explicitly confirmed.

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 concise, consisting of two sentences. The first sentence packs detailed information about the report's contents into a list, and the second states the citation. It front-loads the resource name and avoids fluff, though the first sentence is a bit dense and could be structured as a clearer action statement (e.g., 'Returns the...'). Overall, every word earns its place.

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 simplicity (zero parameters, no output schema, no annotations), the description is quite complete. It thoroughly explains what the report contains, its license, and how to cite it. However, it does not explicitly mention the return format (e.g., plain text, JSON, HTML) or whether the citation is mandatory for execution, but the core purpose and expected output are well covered.

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 input schema is empty. The baseline for zero parameters is 4, and the description appropriately provides no parameter-specific details since there are none to describe.

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 specifies the resource ('The Defender Scoreboard report') and its content (exploited vs detectable vs patchable, figures with method, caveat, denominator, corpus block, method-change notes). The verb 'get' is provided by the tool name, making the action obvious. It distinguishes this tool from siblings like get_cve, get_updates, and search_cves by focusing on the scoreboard report.

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 when to use this tool—if you need scoreboard statistics or the report—but it does not explicitly state when to prefer it over alternatives, nor does it mention any exclusions or contraindications. Sibling tools are not referenced, so the usage guidance is only inferred from the content 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 transparency burden. It discloses important behaviors such as 'strictly-after' semantics, the use of next_cursor for continuation, and that events for withdrawn CVE ids are omitted. It does not cover auth or rate limits, but these are not core for a simple stream.

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 three sentences, front-loaded with the tool's purpose, followed by concise pagination instructions and an edge-case note. Every sentence earns its place with no redundancy 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?

Given the tool's moderate complexity (pagination, time semantics, filtered events), the description covers the essential workflow. It lacks a description of the response format (no output schema) and limit defaults, but the provided details are sufficient for core usage.

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 explain parameters. It explains 'since' and the cursor (via next_cursor), but does not describe 'limit' or elaborate on the 'type' enum beyond listing the values. The enum values are self-explanatory, so some weight is given, but the gap keeps this at a 3.

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 defines the tool as a publication change stream, listing the specific timestamp fields it returns. This distinguishes it from sibling tools like get_cve and search_cves, which are for individual lookups or searching, not streaming changes.

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 gives explicit usage instructions: 'Pass since (YYYY-MM-DD, strictly-after) on the first call, then the returned next_cursor to continue.' This is clear context for how to paginate, though it does not name alternative tools or explicitly state when to use this over them.

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 and does so thoroughly. It discloses the response format (KEV-first, verbatim OSV ranges), the meaning of 'fixed' vs 'affected_through', the limitation that it does not evaluate version membership, and the caveat that absence is not safety evidence.

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?

Though dense, every sentence earns its place: purpose, input forms, output format, semantics, and caveats. The description is well-structured with an initial purpose, then key nuances, and ends with coverage limitation.

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 having no output schema, the description explains the return structure in detail (CVE list, events, projections) and critical behavioral constraints. It covers input combinations, version handling, and data source scope, making it highly complete for a 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?

The schema already covers all parameters (100% coverage), so baseline is 3. The description adds value by explaining the relationship between purl and ecosystem/name, giving concrete examples (pkg:npm/lodash, Maven group:artifact), and emphasizing verbatim package naming.

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 identifies the tool as querying CVEs for a single open-source package, with specific input modes (purl or ecosystem+name). The phrase 'one open-source package' distinguishes it from broader sibling tools like search_cves or get_scoreboard.

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 states the exact input forms (purl vs ecosystem+name) with examples, implying when to use this tool. It also provides a critical caveat about not evaluating version membership. However, it does not explicitly mention alternative sibling tools or when not to use this one.

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 provided, the description carries the full burden of disclosing behavior. It explains important nuances: the meaning of fix=0 ('computed-and-none-held, never no fix exists'), what detect tracks ('detection content we track'), and the ordering for filter-only queries (KEV-first then EPSS). This adds valuable context, though it does not cover all possible behavioral aspects like rate limits or output shape.

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 dense but efficiently structured. It starts with the main purpose ('Search the catalog') and then lists filters in a logical, comma-separated fashion with inline explanations. Every sentence adds information, and the length is appropriate for the tool's 14 parameters. There is no redundancy 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?

Given the complexity (14 parameters), absence of annotations, and no output schema, the description is remarkably complete. It covers the search scope, all input semantics, special behaviors (fix=0, ordering), and a pointer to an alternative tool. It even notes the default ordering for filter-only queries. This leaves the agent well-equipped to decide when and how to invoke the 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?

The input schema has no descriptions, and the description fully compensates by explaining each parameter's format, allowed values, and examples. For instance, it clarifies vendor as a slug, cwe as 'CWE-nnn', year as '2024,2025', sev as 'critical,high', and epss_gte as 0..1. It also provides a concrete package example and notes the limit range. This goes far beyond the bare 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 clearly states the tool's function: 'Search the catalog.' It specifies that it supports free text and structured filters, and it differentiates from sibling tools by noting that for package ranges, one should use query_package. This makes the purpose unambiguous and distinct from other 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 provides clear usage context by enumerating the filter parameters and explaining filter-only query behavior. It explicitly points to query_package for ranges, offering an alternative. However, it does not explicitly state when NOT to use this tool (e.g., for retrieving a single CVE, use get_cve), so it falls short of a full 5.

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