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

Annotations already declare readOnlyHint, idempotentHint, and destructiveHint false, so the safety profile is covered. The description adds valuable context by clarifying that it is a security contract description, not a claim of deployment security, which sets accurate expectations for the agent.

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 (machine-readable description of the trust model) and then a clarifying caveat. There is no unnecessary verbosity; every sentence 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 no-parameter, read-only tool without an output schema, the description is sufficient: it states what the tool provides and warns against over-interpretation. It could specify the exact output format, but 'machine-readable' gives a reasonable hint, and the low complexity keeps this from being a major 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?

The tool has zero parameters, so the description need not explain parameter behavior. According to the rubric, a 0-parameter tool gets a baseline of 4, and the description does not introduce any confusing parameter-related language.

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 provides a machine-readable description of the v17 Cognitive Membrane trust model, listing its key components (origin-bound authority, task-scoped exact-call capabilities, replay protection, egress control, two-phase effectful actions). This is specific and distinguishes it from siblings that likely perform operations or assessments rather than describe a security model.

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 when to use it (to understand the trust model) and explicitly states what it is not (proof of vulnerability-free deployment), which suggests it is not for security auditing. However, it does not name alternative tools like mithrandir_assess or mithrandir_inspect, leaving some ambiguity about exactly which sibling to use for vulnerability checks.

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