Threatist

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

Annotations already declare readOnlyHint, idempotentHint and openWorldHint=false, so safety and idempotency are covered. The description adds that the result bundles the advisory's CVEs and records, which is useful return-content context in the absence of an output schema, but says nothing about lookup failure behavior (e.g., unknown id) or result size.

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?

It is short and front-loaded with the supported advisory types, but it is a sentence fragment that reads as a label rather than an instruction, so the brevity comes at the cost of clarity. No filler, but also no actionable framing.

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 one-parameter read tool with full annotations and full schema coverage, the essential lookup contract is implied and the return contents are sketched. Missing is any routing guidance against the similarly-scoped siblings, which is the main thing an agent still needs.

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% and the single id parameter is documented with concrete examples (RHSA-2024:0001, KB5034441, ADV240001). The description adds no further meaning about the id format or accepted prefixes, so the schema does all the work and baseline 3 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 names the resource scope (Red Hat RHSA, Microsoft KB/ADV advisories) but is a bare noun phrase with no verb, so the agent must infer that this is a fetch-by-id operation from the name and schema. It does not differentiate itself from siblings like get_vulnerability or get_vendor, which also return CVE-related data.

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 when-to-use guidance at all: no statement of when to pick this over get_vulnerability, get_vendor, or search_vulnerabilities, and no prerequisite or exclusion conditions. The agent must deduce routing from the resource names alone.

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 state readOnlyHint, idempotentHint and closed-world, so the safety profile is covered. The description adds ordering behavior ("highest priority first"), but that sits awkwardly next to the sort parameter without clarifying whether it is a default or a hard rule, and it says nothing about pagination despite a cursor parameter.

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, with the scope stated before the filter reference. Nothing needs to be trimmed.

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 17 parameters, only one required, and no output schema, the description is thin: it never says what a "record" is, what fields come back, or how pagination behaves. Delegating filter explanation to search_vulnerabilities is efficient but leaves the return shape entirely undocumented.

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% and every parameter, including vendor formatting and cursor semantics, is documented in the schema. The description only adds the pointer that the filter set mirrors search_vulnerabilities, which is marginally useful but not new semantics; baseline 3 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?

"A vendor's records" names the resource and the scope (per-vendor) and the phrase "takes the same filters as search_vulnerabilities" positions it against a named sibling. However, "records" is vague about what is returned (vulnerabilities? advisories?), so the agent must infer the entity type.

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?

Referencing search_vulnerabilities implies this is the vendor-scoped variant of that search, which hints at when to pick it. But there is no explicit "use this when you want results limited to one vendor; use search_vulnerabilities otherwise" statement, and no exclusions versus get_vulnerability or list_exploited.

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 cover read-only and idempotent, so the bar is lower, but the description goes further: it discloses that results are truncated by default (no CPE matches, max 20 references with exploits and patches prioritized, 10 newest advisories) and that a 'trimmed' indicator reports what was removed. This is exactly the kind of non-obvious output-shaping behavior an agent needs before deciding whether to set full=true.

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 tight sentences with no filler; the truncation default and the trimmed indicator are front-loaded before the parameter note. The opening fragment lacks a verb, which slightly hurts immediate parseability but costs no padding.

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 two-parameter read-only lookup with no output schema, the description covers the lookup keys, alias handling, merged-id resolution, default truncation, and the trimmed metadata field. Remaining gaps (error behavior for unknown ids, exact structure of the trimmed field) are minor.

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 baseline is 3, and the description earns an extra point by explaining the default state of the optional full parameter (shortened record) and what 'full' restores, plus the accepted alias forms for id. It adds semantics about the default that the schema only implies.

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 the resource precisely (a vulnerability record retrievable by Threatist id or by an alias like CVE/GHSA) and explains the merged-id case. It is a noun phrase rather than a verb, but the resource and lookup key are unambiguous enough to distinguish it from siblings like search_vulnerabilities or get_advisory.

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 only implied: an agent can infer this is the direct-lookup tool versus a search tool, but the description never states when to prefer it over search_vulnerabilities, list_exploited, or get_advisory. The only explicit when-condition is the indirect hint that the default is trimmed unless full detail is 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?

Annotations already declare readOnly, idempotent and closed-world, so the description doesn't need to restate safety. It adds genuine value by disclosing the sort order (newest first) and that each entry carries its Threatist record, which is context the annotations cannot supply.

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 short sentences, front-loaded with the resource and immediately followed by ordering and payload. The phrase "its Threatist record" is unexplained jargon, the only minor drag.

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?

Three optional parameters and no output schema mean the description should hint at return shape, and it does only vaguely ("each with its Threatist record"). Pagination via cursor and the effect of the since window on results are left entirely to the 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 coverage is 100% with per-parameter descriptions including defaults and the since enum, so the schema does the heavy lifting. The description adds nothing about limit, since or cursor semantics; baseline 3 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?

Names a specific resource — recent additions to CISA's Known Exploited Vulnerabilities catalogue — and states ordering (newest first). It is clearly distinct from get_vulnerability and search_vulnerabilities, though it never explicitly contrasts itself with them.

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?

"Recent additions" implies a browse-the-newest use case, which is enough to infer intent, but there is no explicit when-to-use-this vs search_vulnerabilities guidance and no statement of what it cannot do (e.g. query by keyword or vendor).

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, idempotentHint, and openWorldHint=false, so safety and repeatability are covered. The description adds the paging contract (results come page by page, continue via cursor), which is genuinely useful context beyond the annotations. It does not disclose ordering defaults, result size defaults, or whether the search is exhaustive, so it remains thin for a 17-filter query tool.

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 short sentences, front-loaded with the result description and followed immediately by the pagination instruction; no filler or repetition. The terseness costs some clarity ("Records" instead of "vulnerabilities") but nothing is wasted.

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 17-parameter, zero-required search tool with no output schema, the description covers pagination but leaves the shape and termination of results implicit, and never clarifies that all filters are optional and combinable. The 100% schema coverage carries most of the burden, so this is adequate rather than 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 description coverage is 100%, so every one of the 17 filters is already documented in the input schema, justifying the baseline 3. The description only adds the cross-reference that the previous page's "next" value goes into the cursor parameter — helpful but phrased with a field name ("next") that does not appear in the input schema and is unexplained without an output 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 gives a verb-less framing ("Records matching a text and filters, a page at a time") and never names the resource as vulnerabilities, so the reader must infer the domain from the tool name. It also does not distinguish this from siblings like get_vulnerability or list_exploited. It is understandable but vague on 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?

There is no statement of when to use this search versus get_vulnerability, list_exploited, or get_advisory. The only actionable instruction is pagination-related ("Pass next as cursor for the next page"), which addresses how to continue, not when to choose this tool. No prerequisites, no exclusion of overlapping tools.

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