mitre-cwe-mcp-server

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

Annotations only cover read-only/idempotent/open-world, while the description discloses the 24,000-byte budget, deferred-ID reporting, omission of default sections with a named size and 'kind partial' re-call, per-item notFound behavior for CWE IDs, whole-call rejection triggers, and the caveat that recorded ATT&CK mappings are not current validation. That is substantial behavior beyond structured fields.

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?

Purpose and ID formats are front-loaded and nearly every clause carries a distinct constraint. It is, however, a single semicolon-chained block that is hard to parse for a tool with this many conditional behaviors; light structure would improve it without adding length.

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 batched lookup with an output schema already defining return shape, the description covers the remaining risks: budget truncation, section defaults, per-item error handling, and mapping reliability. Nothing an agent needs to call it correctly is missing.

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 earns above that by documenting the default section set for patterns (summary, prerequisites, execution, mitigations, mappings) versus categories/views (summary plus relations in source order or XPath filterDefinition), which the schema never states. It also explains the notes section as outside the defaults.

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 (retrieve) and resource (CAPEC attack patterns, categories, views) plus accepted ID forms (CAPEC-66, CAPEC66, 66) and the fact that Deprecated/Obsolete records are included. An agent can tell this is a by-ID lookup rather than the sibling cwe_search_attack_patterns sweep without opening the schema.

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?

Gives clear operating context: up to 20 distinct IDs per call, empty array requests an outline, and CAPEC-1000/CAPEC-3000 are named as entry points for browsing by category. It stops short of explicitly routing to cwe_search_attack_patterns when IDs are unknown, so there is no stated alternative path.

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 only say readOnly/idempotent/openWorld; the description goes well beyond them by explaining edge orientation (parent to child with view identity retained), cursor continuation semantics including re-fetch and rejection of changed topology, that empty relations succeed while upstream failures error, and that node names may lag live IDs. These are non-obvious behaviors an agent could not infer from structured fields.

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?

Purpose leads, then discovery, then parameter rules, then edge/pagination semantics, then error and freshness caveats – a sensible ordering with no filler. The telegraphic clauses about topology rejection and catalog lag are dense but each carries real information rather than 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?

With six parameters, an output schema, and full annotation coverage, the description supplies exactly the missing behavioral layer: pagination, error/success distinctions, and catalog staleness. Nothing needed to call the tool correctly is absent.

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 already documents id format, limit caps, cursor opacity, viewId default/all, and primaryOnly's restriction, so the description's viewId/primaryOnly notes largely restate the schema. Only the cursor follow-next and default-view framing add slight value, so the 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 first sentence gives a specific verb (navigate) plus resource (CWE hierarchy) and enumerates the four relation types, so an agent immediately knows this is traversal, not lookup. It explicitly routes ID discovery to cwe_search_weaknesses and cwe_list_reference, separating it from the get_* siblings that return a single node.

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 states how to obtain IDs, what the default view is (1000), how to span all views (viewId all), and that primaryOnly is valid only for ancestors. What it doesn't do is contrast traversal with cwe_get_weakness/cwe_get_view when the agent already has an ID, so the when-not-to-use case is left implicit.

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 only say readOnly/idempotent/openWorld; the description adds real behavioral knowledge beyond that: navigation views truncate to top-level members, Implicit views return no members at all, unknown or non-view IDs yield a structured miss, and unparseable filter parts produce a disclosure-backed empty result. It also discloses pagination semantics via nextCursor, which is non-obvious for a 'direct members' list.

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?

Front-loaded with the core purpose, then edge cases; every sentence carries substantive routing or behavior information. There is mild redundancy, since weakness-membership-via-search is restated for the navigation and Implicit cases, but nothing is 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?

With an output schema present, the description correctly avoids describing return shapes and instead covers the decision-relevant edge cases: truncation, empty Implicit views, structured misses, pagination, and unevaluated filter parts. Nothing an agent needs to call this correctly in a knowledge-graph context is missing.

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 meaning the schema does not: cursor pagination is scoped to 'remaining direct members' rather than any other collection, and it clarifies what a filter view's filterDefinition represents. The limit parameter's cap and byte budget are left entirely to 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?

States a specific verb ('Read') and resource (a CWE view) and enumerates exactly which fields are returned (objective, audience, status, source filter, notes, direct members). It also draws the boundary against cwe_get_hierarchy and cwe_search_weaknesses, so an agent can distinguish it from siblings without opening any schema.

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?

Explicitly routes: 'use cwe_get_hierarchy for navigation or cwe_search_weaknesses with viewId for weakness membership closure,' which names both alternatives and the conditions that select them. It further explains the Implicit/filter-defined case where the correct alternative is the search tool, including the case where the filter part isn't evaluated.

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?

On top of readOnly/openWorld/idempotent annotations, the description discloses a great deal of behavior beyond them: a 20-distinct-ID cap inside a 24,000-byte budget with deferred IDs named, whole-section omission marked with size and 'kind partial', completion guarantees for explicit sections including oversized records, and precise rejection rules (control characters, non-ID items over 150 characters). This is exactly the context an agent needs to interpret a partial result rather than retry blindly.

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?

Nearly every clause carries information, but the middle sentences are long semicolon-chained runs that are hard to parse on first read, and the example-paging semantics are restated across the description and multiple schema fields. The single most important fact (batch limits) is front-loaded, but overall structure is dense rather than crisp.

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 an output schema present, rich annotations, and full schema coverage, the description rounds out the remaining gaps: budget behavior, partial-result semantics, rejection conditions, default vs explicit section behavior, and example paging. An agent can call this correctly and interpret truncated responses without further documentation.

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 property descriptions already repeat much of the budget and example-paging semantics, so the baseline is 3. The description still adds value by explaining the interaction rules -- that example parameters are ignored under explicit sections, that paging is source-ordered and language-filtered, and that the page is outlined with its size and a re-call -- which the schema only states piecemeal.

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 opening sentence gives a specific verb and resource plus concrete accepted ID formats (CWE-79, CWE79, 79), and closes by clarifying that categories are organizational entries rather than root causes. Sibling differentiation is only implicit -- it notes that a view or CAPEC ID lands in notFound, which gestures at cwe_get_view / cwe_get_attack_pattern without naming 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?

The description establishes clear operating context: defaults when sections is omitted, an outline for an empty array, and that explicit sections without examples ignore the example parameters. It also functions as a soft exclusion by stating that views and CAPEC IDs return in notFound with recovery guidance, but it never explicitly routes the agent to cwe_search_weaknesses for discovering IDs.

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 the safety profile (readOnly, idempotent, openWorld), and the description adds behavior beyond them: page caps above 100 with disclosure and the need to follow nextCursor for exhaustive lists. It does not mention ordering of results or what an empty page means, which keeps it from a 5.

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?

Front-loaded with the resource scope, then filter and pagination behavior, with no filler sentences. The second sentence ("Platforms distinguishes example code languages from platform names and classes") is compressed to the point of being hard to parse on first read.

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 an output schema, full schema descriptions, and annotations present, the description only needs to add routing and behavioral context, which it does for filtering, capping, and pagination. Coverage of how the topics relate to sibling tools is the remaining gap.

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 earns above that by explaining the non-obvious filter matching rule (tokens match at word starts or camelCase humps, with the "script finds JavaScript" example) and by clarifying that platforms mixes example-code languages with platform names and classes. The limit cap and cursor semantics largely repeat 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?

Opens with a specific verb and resource ("List loaded CWE/CAPEC vocabulary") and enumerates the topic families it covers, which clearly separates it from the get_/search_ siblings. The trailing "or" chaining of views, workflow, and versions makes it read as a grab-bag rather than a crisp statement of one purpose, so it falls short of 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?

"omit filter to browse" plus "Follow nextCursor for complete lists" gives concrete when-to guidance for the two main usage modes. It stops short of explicitly routing the agent away from cwe_search_weaknesses or cwe_get_view, so there is context but no 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?

Beyond the readOnly/openWorld/idempotent annotations, the description discloses token-matching semantics (word-start only, never mid-word), that parent ATT&CK techniques include recorded subtechniques, that CWE mappings are exact with no hierarchy expansion, that Deprecated/Obsolete records are excluded by default, and the precise result ordering. It even warns that mappings are incomplete and do not validate current ATT&CK coverage — a real caveat an agent needs.

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?

Front-loaded with the search surface and back-loaded with ordering and paging guidance, with no filler sentences. It is somewhat dense and restates the word-start token rule that the filter parameter schema already documents, a minor 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 9-parameter search tool with an output schema, the description covers the behavioral edges an agent would otherwise get wrong: default exclusion of inactive patterns, no hierarchy expansion on CWE, incomplete mappings, deterministic ordering, and cursor continuation. Nothing needed to call it correctly is missing.

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; the description adds meaning on top by clarifying that CWE filters are exact-without-hierarchy and that attack-technique filters roll up parent techniques, which the schema does not say. It does not explain how to discover severity/likelihood values in the description (that hint lives only in the schema), so it stops short of a 5.

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 and resource (search CAPEC attack patterns) plus the full set of searchable dimensions. It explicitly routes to the sibling cwe_get_attack_pattern for complete sections, so an agent can distinguish it from related tools without opening 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?

"Omit filters to browse" gives the no-filter case, "use cwe_get_attack_pattern for complete sections" names the alternative and its condition, and "follow nextCursor for remaining matches" covers the paging case. Usage is fully specified rather than inferred.

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 mark it read-only, idempotent, and open-world. The description adds substantive behavior beyond that: categories are excluded, results are ordered by match quality and then ID, result previews contain only the first sentence, and matching mapping/observed-example details appear under taxonomy or CVE filters.

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 front-loaded with purpose and searchability, then covers matching, exclusions, result shape, and pagination. It is dense and mostly earns its length, though several token-matching details duplicate the schema and could be tightened.

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 13 optional parameters, a fully documented schema, an output schema, and strong annotations, the description supplies everything needed: browse behavior, matching semantics, exclusions, result composition, ordering, and continuation via cursor.

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 the schema already explains nearly every parameter in detail, including token matching, taxonomy mapping conjunction, CVE exactness, and view semantics. The description adds little parameter meaning beyond the schema, so the high-coverage baseline of 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?

Opens with a specific verb and resource: search CWE weaknesses, then enumerates the dimensions by which it can search. This clearly distinguishes it from cwe_get_weakness (full sections) and cwe_search_attack_patterns (different resource).

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?

Explicitly says to omit filters to browse, that categories are excluded, and that cwe_get_weakness should be used for complete sections. It also explains following nextCursor and how to discover filter values, giving clear alternatives and conditions.

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