MITRE ATT&CK MCP Server

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

No annotations are provided, so the description carries the full burden of behavioral disclosure. It mentions the domain restriction ('only pertains to ICS domain') and the optional 'include_description' parameter, but doesn't describe other critical behaviors: what the output looks like (e.g., list of assets with IDs/names), whether it's a read-only query (implied by 'Get' but not explicit), error conditions, or rate limits. For a tool with no annotations, this leaves significant gaps in understanding how it behaves.

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 well-structured and concise: a clear purpose statement followed by an 'Args:' section with parameter explanations. Every sentence earns its place, and there's no redundant information. It could be slightly more front-loaded by integrating the domain restriction into the first sentence, but overall it's efficient and readable.

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 (a query tool with 3 parameters, no annotations, and no output schema), the description is moderately complete. It explains the purpose, parameters, and domain restriction, but lacks output details (what assets are returned, in what format) and behavioral context (e.g., read-only nature, error handling). For a tool with no structured support, it should do more to compensate, but it meets minimum viability for basic 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?

The schema description coverage is 0%, so the description must compensate. It provides clear semantics for all three parameters: 'technique_stix_id' (Technique STIX ID to check what assets are targeted by it), 'domain' (Domain name 'ics'), and 'include_description' (Whether to include description in the output). This adds meaningful context beyond the bare schema, though it doesn't detail format constraints (e.g., STIX ID pattern) or explain the default for 'domain'. Since it covers all parameters adequately, it scores above baseline.

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: 'Get assets targeted by technique STIX ID (shows how assets are targeted by technique)'. It specifies the verb ('Get'), resource ('assets'), and relationship ('targeted by technique'), and distinguishes it from siblings like 'get_all_assets' or 'get_techniques_targeting_asset'. However, it doesn't explicitly differentiate from all similar tools (e.g., 'get_techniques_targeting_asset' is the inverse), so it's not a perfect 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?

The description provides some usage context: 'only pertains to ICS domain' and implies it's for querying asset targeting. However, it doesn't explicitly state when to use this tool versus alternatives like 'get_techniques_targeting_asset' (which queries the inverse relationship) or 'get_all_assets' (which lists all assets). The guidance is implied rather than explicit, lacking clear exclusions or named alternatives.

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