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

Annotations already declare readOnlyHint=true and openWorldHint=true, and the description adds pagination support and the option to return only a count. These are behavioral traits beyond what annotations provide, with no contradictions.

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 sentences, front-loaded with the core purpose, followed by key capabilities. Every sentence earns its place with no redundancy.

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 read-only lookup with fully documented parameters and no output schema, the description covers the main behavioral options (pagination, count mode) and a clear use case. It doesn't detail return format, but given the simplicity and annotation coverage, this is adequate.

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 all four parameters are documented in the schema. The description mentions pagination and count, but these are already covered in the schema descriptions, so it adds minimal semantic value beyond what is structured.

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 specific verb 'Search' and resource 'CPE entries' within 'Shodan's CVEDB'. It distinguishes from the sibling cves_by_product by focusing on CPEs rather than CVEs, and the name reinforces this.

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 a clear use case: 'identifying specific versions and configurations of software and hardware.' However, it does not explicitly mention alternatives or exclusion criteria. The sibling cves_by_product likely covers CVEs, so the contrast is implied but not stated.

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 and openWorldHint, covering safety and openness. The description adds substantial behavioral context by listing the specific fields returned (CVSS v2/v3, EPSS, KEV status, mitigations, ransomware associations, CPEs), which goes beyond the annotations and helps the agent set expectations.

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 sentences with zero fluff. The first sentence front-loads the core purpose, and the second enumerates the key return fields. Every clause 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?

For a single-parameter lookup tool with no output schema, the description adequately covers the return content by listing the major fields. It does not mention error handling or pagination, but given the simplicity and the openWorldHint annotation, the essential information is present. Minor gaps prevent a 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 input schema fully describes the parameter (pattern and description), so schema coverage is 100%. The description does not add new parameter semantics beyond what the schema already provides; it merely reinforces that a CVE ID is needed. With full schema coverage, 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 states a specific verb ('Query') and resource ('detailed vulnerability information from Shodan's CVEDB'), and enumerates the concrete data returned (CVSS, EPSS, KEV, mitigations, ransomware, CPEs). This clearly distinguishes it from siblings like cves_by_product, which likely searches by product.

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 when you have a CVE identifier (the required parameter), but it does not explicitly mention when not to use it or recommend alternatives like cves_by_product for product-based queries. Guidance is implicit rather than explicit.

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=true and openWorldHint=true, so the tool is known to be a read-only, broad-scope operation. The description adds value by disclosing the return content ('detailed vulnerability information including severity scores and impact assessments') and mentions pagination support, which goes beyond the annotations. It does not contradict any annotation.

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 sentences, with the primary purpose front-loaded and the supporting capabilities summarized in the second sentence. It is not overly verbose, though the second sentence packs multiple features into one clause. No extraneous information is present, and the structure is logical.

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 (9 parameters, all with schema descriptions) and the absence of an output schema, the description provides a sufficient overview, including the two search modes (product name vs. CPE identifier) and the return of severity/impact info. It could be more explicit about the relationship between product and cpe23 (e.g., whether they can be combined), but overall it covers the key usage context.

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 each parameter is already documented in the schema (e.g., skip, count, cpe23, limit, is_kev, product, dates, sort_by_epss). The description adds only a high-level summary (supports filtering by KEV, sorting by EPSS, date ranges, pagination) without adding new semantic detail. This aligns with the baseline of 3 for fully covered schemas.

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 ('Search') and a precise resource ('vulnerabilities affecting specific products or CPEs'), and lists the supported filtering/sorting capabilities. This clearly distinguishes it from sibling tools like cve_lookup (individual CVE lookup) and cpe_lookup (CPE details), making its purpose unambiguous.

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 conveys that this tool is for product/CPE-based vulnerability searches and mentions the search options (by product name or CPE 2.3). However, it does not explicitly state when to prefer this over sibling tools, such as using cve_lookup for a specific CVE or cpe_lookup for CPE metadata. The guidance is implied rather than explicit, so it earns a 3.

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, so the description isn't required to state safety. It adds the batch resolution feature and the mapping behavior, which is useful context. No contradictions.

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 sentences, no waste, key purpose first.

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 tool with no output schema, the description covers purpose, behavior, and return format adequately. No gaps for an agent to call it correctly.

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 covers the parameter fully (100%). Description adds the 'batch' nuance but essentially repeats the schema's 'list' semantics. 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?

States a specific verb (Resolve), resource (domain names to IP addresses), and names the service (Shodan's DNS). Implicitly differentiates from reverse_dns_lookup by direction.

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?

Implied usage: if you need to resolve domain names to IPs, this is the tool. But no explicit when-not-to-use or alternatives mentioned. Batch capability is mentioned but not as a selection criterion.

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 accurately reflects a read-only lookup operation and adds helpful qualifiers like 'if available' and 'when present.' It does not contradict the readOnlyHint annotation, though it omits potential error or rate-limit behavior.

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 sentences, free of fluff, and front-loads the core purpose before listing specific return categories.

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?

With no output schema provided, the description usefully enumerates expected return data. It lacks error/edge-case details, but the listed outputs give sufficient context for typical use.

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 ip parameter as 'The IP address to query,' and the description repeats this without adding format constraints, IPv4/IPv6 guidance, or examples. Schema coverage is effectively complete, so baseline score 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?

Clearly states the tool retrieves comprehensive information about an IP address and enumerates the types of data returned (geolocation, open ports, services, SSL certificates, hostnames, cloud details). This distinguishes it from sibling tools like dns_lookup 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 makes the tool's scope clear but does not explicitly state when to use it over alternatives such as shodan_search or dns_lookup. Usage guidance is implied rather than stated.

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 and openWorldHint, so the safety profile is covered. The description adds behavioral context beyond annotations: it supports batch queries, returns all known hostnames per IP, and provides clear indication when none are found. This is useful operational detail that the schema and annotations do not convey.

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, no filler. The first sentence states the core purpose, the second adds batch and return details. Information is front-loaded and 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?

This is a simple one-parameter tool with a clear return description. The description explains what the tool does, how it handles multiple IPs, and what it returns (hostnames and a not-found indication). Annotations cover read-only and open-world aspects. Nothing essential for correct invocation is missing, even without an output schema.

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%, with the ips parameter clearly documented as a list of IP addresses. The description adds no new semantic meaning—'batch lookups' is implied by the array type. Per the baseline rule for high coverage, a 3 is appropriate; the description does not compensate or add value beyond 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 states a specific action (perform reverse DNS lookups), a clear resource (IP addresses), and the expected output (hostnames). It also distinguishes itself from forward DNS lookups by the term 'reverse,' which is reinforced by the sibling dns_lookup. This is unambiguous and not a tautology.

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 for IP-to-hostname resolution but does not explicitly contrast with alternatives like dns_lookup or ip_lookup. It mentions batch support, which is a feature, but offers no when-to-use/when-not-to-use guidance. Usage is inferred from the tool name and context rather than stated.

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 carry the read-only safety profile (readOnlyHint=true, openWorldHint=true), lowering the burden. The description adds value by specifying what results contain (services, vulnerabilities, geographic distribution, country statistics), but it does not disclose operational traits such as API-key requirements or rate limits that matter for a Shodan-backed search.

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 sentences, front-loaded with the primary purpose. Minor redundancy exists in listing return types twice ('services, vulnerabilities, and geographic distribution' and 'country-based statistics'), but overall there is no wasted verbiage.

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?

With no output schema, the description correctly takes on explaining return content, which it does (services, vulnerabilities, geo distribution). However, it omits operational essentials for a network-scanning API—authentication requirements and result pagination—and offers only vague filter syntax guidance, leaving an agent under-informed for a moderately complex 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?

Schema description coverage is 100%, so both query and max_results are already documented. The description adds only a marginal hint that query supports advanced filters, without syntax or examples. This matches the baseline 3 for high-coverage schemas.

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?

States a specific verb+resource ('Search Shodan's database of internet-connected devices') and describes what it returns. It implicitly distinguishes from the lookup siblings (ip_lookup, cve_lookup, etc.) by being a filter/statistics search rather than a single-entity lookup, though this differentiation is not made explicit.

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 mention of 'advanced search filters' and 'country-based statistics' implies this is for broad exploratory searches rather than targeted lookups, but no alternative tool is named and no when-not-to-use conditions are given. An agent must infer the boundary against the six lookup siblings.

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