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

Annotations already declare readOnlyHint=true and destructiveHint=false, so the safety profile is covered. The description adds meaningful behavioral context beyond annotations: it explicitly states the server "never requests your program docs or product roadmap" and "instructs your AI to keep them local," disclosing a privacy posture. It also clarifies that the context flows to the AI for local analysis, which is not implied by the annotations.

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 a single dense sentence, but it is front-loaded with the core action and resource. The enumeration of nine frameworks is verbose yet informative, and the privacy note adds distinct value. No redundant or filler content is present, though splitting into two sentences would improve readability. Overall, every clause contributes.

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 does a good job explaining what the tool loads and why it is useful. It lists the matrix, frameworks, and playbooks, and addresses data privacy. However, it does not describe any return value or side-effect (though for a load_context tool, the primary effect is context injection, which is implied). The description is sufficiently complete for an agent to understand the tool's scope and content.

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%: both parameters (purpose and detail_level) have clear descriptions with enums. The description mentions "evaluation + cross-mapping playbooks," which aligns with the purpose parameter's enum values, but it does not add any syntax, defaults, or nuances beyond what the schema already provides. Thus the 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?

The description opens with a clear verb and resource: "Load Lenny Zeltser's AI Defense Matrix context," and then enumerates the exact contents (8-asset x 6-NIST-CSF-2.0-function matrix, nine cross-walked frameworks, playbooks). This distinguishes it from sibling load_context tools (e.g., cti_load_context, ir_load_context) by naming a specific, unique knowledge domain.

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 no explicit guidance on when to use this tool versus alternatives. It does not mention sibling tools like aidefense_get_matrix or aidefense_evaluate_program, nor does it state prerequisites or contrasting scenarios. The usage context is implied only by the tool's name and the listing of contents, which is insufficient for clear decision-making.

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