Security Intel MCP

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 meaningful behavior: it accepts a raw package.json or a dependencies array, returns per-package findings plus a summary, and defaults the ecosystem to npm. It does not cover edge-case behavior like what happens if both inputs are supplied or if the manifest is invalid, but the core behavior is transparent.

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 cover purpose, input modes, return behavior, and default ecosystem without repetition. The most important purpose statement is front-loaded, and every sentence contributes meaningful 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 description gives a solid high-level picture but leaves gaps: there is no output schema, and the return value is only described as 'per-package findings and a summary' with no detail on structure, severities, or counts. It also does not address ambiguous inputs, such as supplying both manifest and dependencies, or how errors like an invalid package.json manifest are handled.

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, but the description adds real value by clarifying that manifest and dependencies are alternative input modes rather than independent optional fields. It also contextualizes the ecosystem parameter by stating the npm default, which is not inferable from the raw schema alone.

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 opens with a specific verb and resource: 'Audit a whole dependency manifest for known vulnerabilities in one call.' This clearly states what the tool does and its batch-oriented scope, but it does not explicitly differentiate it from the sibling tools cve_lookup or package_vulnerabilities.

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 'in one call' and 'whole dependency manifest' imply this is for bulk manifest auditing, and the description explains how to provide input via manifest or dependencies. However, it never states when to prefer this tool over cve_lookup or package_vulnerabilities, 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 full transparency burden. It does well by disclosing the multi-source nature (NVD, CISA KEV, FIRST EPSS) and enumerating the exact data fields returned. It does not cover edge cases like unknown CVE IDs or output format, but there is no contradiction and the core behavior is clearly communicated.

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 efficient sentences with no fluff. The action and subject are front-loaded, the return fields are compactly enumerated, and every clause adds useful information. Excellent structure.

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 is a straightforward single-parameter lookup, and the description sufficiently explains what will be returned and from which sources. Minor gaps exist because there is no output schema and no mention of invalid-CVE behavior, but for this level of complexity the description is largely complete.

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% (single cve_id with an example), so the baseline is 3. The description restates that the tool looks up a CVE by ID, which adds no semantic depth beyond the parameter name and example. It meets the baseline without exceeding it.

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 a specific action ('Look up a CVE by ID') and a defined resource with a detailed summary of returned data. It does not explicitly differentiate itself from siblings like epss_score or known_exploited, which overlap in the EPSS and KEV content, 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?

Usage is implied: use this when you need a CVE summary. However, the description does not mention when to prefer a specialized sibling tool (e.g., epss_score for EPSS-only, known_exploited for KEV-only), leaving the choice ambiguous given that cve_lookup also returns those data points.

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 present, so the description carries the full burden. It discloses the output (score 0-1, percentile), the time horizon, the source (FIRST.org EPSS), and the input multiplicity. It does not cover rate limits or error behavior, but for a simple read-style API the provided behavioral context is solid.

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 concise sentences, each earning its place: what it returns, when to use it, and how to pass parameters. The source attribution is a useful addition without bloating the text.

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 no output schema, the description appropriately explains both the return values and the decision context. It leaves out exact response formatting for multiple CVEs and the percentile scale, but it supplies enough for an agent to invoke it correctly and interpret the high-level result.

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 adds helpful instructions by mapping cve_id to single CVE use and cve_ids to many, including the array or comma-separated variant. It could be slightly clearer that at least one of the two parameters should be supplied, but the intended usage is clear.

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 verb and resource: get the EPSS exploit-probability score and percentile for one or more CVEs. It also explains the 30-day likelihood meaning, which clearly distinguishes this from generic CVE lookup siblings.

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 says 'Use it to prioritize patching,' giving a clear decision context. It does not explicitly contrast with sibling tools like cve_lookup or known_exploited, but the purpose is specific enough that an agent can infer when this tool is appropriate.

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 behavioral disclosure burden. It adds valuable context: source authority (CISA), freshness (~daily updates), and the two distinct modes of behavior (single check vs. recent list). It does not describe the return format, but the semantics of checking/listing are reasonably inferable.

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 taut sentences with no filler. The primary purpose and source are front-loaded, then the parameter-driven usage pattern is stated directly. Every sentence 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?

The definition covers the tool's purpose, data source, update cadence, and all optional filter behaviors despite no output schema and no annotations. A small gap is the lack of explicit return-shape information (e.g., boolean for a single CVE check, array for listing), but the tool is otherwise fully invokable.

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 baseline is 3. The description adds meaning beyond the schema by explaining the conditional relationship between parameters: cve_id switches the tool from listing mode to check-one mode, and vendor/product and ransomware_only are list-mode filters. That interactional guidance is useful for correct invocation.

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 (CISA KEV catalog), a specific verb (check/list), and the distinguishing semantic (confirmed exploited in the wild). It separates this tool from siblings like cve_lookup and epss_score by defining its unique specialty without requiring the agent to open schemas.

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 gives clear operational guidance: pass cve_id to check one CVE, omit it to list recent entries, and optionally filter by vendor/product or ransomware_only. It does not explicitly name alternatives or say when not to use this tool, so it lacks the full exclusion guidance needed for 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?

The description discloses useful behavioral context: the data source is OSV, version filtering is optional, and only the listed ecosystems are supported. Since there are no annotations, the description carries the transparency burden, but it omits details such as the shape of the returned vulnerability list, empty-result behavior, and any access or rate-limit considerations.

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 two tight sentences with the core action front-loaded and the ecosystem list appended compactly. There is no filler, repetition, or unnecessary detail, making it easy 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?

For a simple three-parameter read tool, the description is mostly sufficient to invoke the tool correctly. However, there is no output schema and the description does not explain what fields the vulnerability results contain, nor does it route the agent away from sibling tools when the context is a dependency audit or a CVE 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%, so the schema already documents name, version, and ecosystem. The description adds a succinct restatement of the optional version and supported ecosystems, but it does not add significant meaning beyond what the input schema already provides.

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, 'List', and identifies a concrete resource: known vulnerabilities for a software package, optionally filtered by version, via OSV. It is distinct from the sibling tools because it is scoped to a package/ecosystem lookup, but it does not explicitly compare itself with audit_dependencies or cve_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 implies the tool's use case: call it when you need OSV vulnerability data for a named package in a supported ecosystem. However, it gives no explicit guidance about when to prefer the sibling tools instead, such as using cve_lookup for CVE IDs or audit_dependencies for dependency-tree auditing.

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